Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.23919/apsipaasc55919.2022.9980290

researchmap

Other Link： https://arxiv.org/abs/2209.04077

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electronics, Information and Communications Engineers (IEICE)  

In this paper, we propose a new algorithm to generate Speech-like Emotional Sound (SES). Emotional expressions may be the most important factor in human communication, and speech is one of the most useful means of expressing emotions. Although speech generally conveys both emotional and linguistic information, we have undertaken the challenge of generating sounds that convey emotional information alone. We call the generated sounds "speech-like," because the sounds do not contain any linguistic information. SES can provide another way to generate emotional response in human-computer interaction systems. To generate "speech-like" sound, we propose employing WaveNet as a sound generator conditioned only by emotional IDs. This concept is quite different from the WaveNet Vocoder, which synthesizes speech using spectrum information as an auxiliary feature. The biggest advantage of our approach is that it reduces the amount of emotional speech data necessary for training by focusing on non-linguistic information. The proposed algorithm consists of two steps. In the first step, to generate a variety of spectrum patterns that resemble human speech as closely as possible, WaveNet is trained with auxiliary mel-spectrum parameters and Emotion ID using a large amount of neutral speech. In the second step, to generate emotional expressions, WaveNet is retrained with auxiliary Emotion ID only using a small amount of emotional speech. Experimental results reveal the following: (1) the two-step training is necessary to generate the SES with high quality, and (2) it is important that the training use a large neutral speech database and spectrum information in the first step to improve the emotional expression and naturalness of SES.

DOI： 10.1587/transinf.2021edp7236

Web of Science

researchmap

Other Link： https://www.webofscience.com/wos/woscc/full-record/WOS:000852731400008

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/icce53296.2022.9730332

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：ASTES Journal  

DOI： 10.25046/aj060519

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ISCA  

The biggest obstacle to develop end-to-end Japanese text-to-speech (TTS) systems is to estimate phonetic and prosodic information (PPI) from Japanese texts. The following are the reasons: (1) the Kanji characters of the Japanese writing system have multiple corresponding pronunciations, (2) there is no separation mark between words, and (3) an accent nucleus must be assigned at appropriate positions. In this paper, we propose to solve the problems by neural machine translation (NMT) on the basis of encoder-decoder models, and compare NMT models of recurrent neural networks and the Transformer architecture. The proposed model handles texts on token (character) basis, although conventional systems handle them on word basis. To ensure the potential of the proposed approach, NMT models are trained using pairs of sentences and their PPIs that are generated by a conventional Japanese TTS system from 5 million sentences. Evaluation experiments were performed using PPIs that are manually annotated for 5,142 sentences. The experimental results showed that the Transformer architecture has the best performance, with 98.0% accuracy for phonetic information estimation and 95.0% accuracy for PPI estimation. Judging from the results, NMT models are promising toward end-to-end Japanese TTS.

DOI： 10.21437/interspeech.2021-914

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier BV  

DOI： 10.1016/j.specom.2020.11.004

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/tencon50793.2020.9293766

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ISCA  

DOI： 10.21437/interspeech.2020-2064

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/icassp40776.2020.9053371

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ISCA  

DOI： 10.21437/Interspeech.2018-1239

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/apsipa.2017.8282238

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：International Speech Communication Association  

In this paper, using GMM-based voice conversion algorithm, we propose to generate speaker-dependent mapping functions to improve the intelligibility of speech uttered by patients with a wide glossectomy. The speaker-dependent approach enables to generate the mapping functions that reconstruct missing spectrum features of speech uttered by a patient without having influences of a speaker's factor. The proposed idea is simple, i.e., to collect speech uttered by a patient before and after the glossectomy, but in practice it is hard to ask patients to utter speech just for developing algorithms. To confirm the performance of the proposed approach, in this paper, in order to simulate glossectomy patients, we fabricated an intraoral appliance which covers lower dental arch and tongue surface to restrain tongue movements. In terms of the Mel-frequency cepstrum (MFC) distance, by applying the voice conversion, the distances were reduced by 25% and 42% for speakerdependent case and speaker-independent case, respectively. In terms of phoneme intelligibility, dictation tests revealed that speech reconstructed by speaker-dependent approach almost always showed better performance than the original speech uttered by simulated patients, while speaker-independent approach did not.

DOI： 10.21437/Interspeech.2017-841

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.1109/APSIPA.2017.8282231

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery, Inc  

In this study, in order to develop a monitoring system that takes into account privacy issues, we investigated user preferences in terms of the monitoring and privacy protec-tion levels. The people on the monitoring side wanted the monitoring system to allow them to monitor in detail. Con-versely, it was observed for the people being monitored that the more detailed the monitoring, the greater the feelings of being surveilled intrusively. Evaluation experiments were performed using the location data of three people in differ-ent living areas. The results of the experiments show that it is possible to control the levels of monitoring and privacy protection without being affected by the shape of a living area by adjusting the quantization level of location informa-tion. Furthermore, it became clear that the granularity of location information satisfying the people on the monitored side and the monitoring side is different.

DOI： 10.1145/2968219.2971412

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Association for Computing Machinery, Inc  

We propose a lifelog browsing system through which users can share memories of their experiences with other users. Most importantly, by using global positioning system data and time stamps, the system simultaneously displays a variety of log information in a time-synchronous manner. This function empowers users with not only an easy interpretation of other users' experiences but also nonverbal notifications. Shared information on this system includes photographs taken by users, Google street views, shops and restaurants on the map, daily weather, and other items relevant to users' interests. In evaluation experiments, users preferred the proposed system to conventional photograph albums and maps for explaining and sharing their experiences. Moreover, through displayed information, the listeners found out their interest items that had not been mentioned by the speakers.

DOI： 10.1145/2968219.2971401

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper presents a sound collection system that uses crowdsourcing to gather information for visualizing area characteristics. First, we developed a sound collection system to simultaneously collect physical sounds, their statistics, and subjective evaluations. We then conducted a sound collection experiment using the developed system on 14 participants. We collected 693,582 samples of equivalent Aweighted loudness levels and their locations, and 5,935 samples of sounds and their locations. The data also include subjective evaluations by the participants. In addition, we analyzed the changes in sound properties of some areas before and after the opening of a large-scale shopping mall in a city. Next, we implemented visualizations on the server system to attract users' interests. Finally, we published the system, which can receive sounds from any Android smartphone user. The sound data were continuously collected and achieved a specified result.

DOI： 10.1109/ICMEW.2016.7574694

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：OKAYAMA UNIV MED SCHOOL  

A palatal augmentation prosthesis (PAP) is used to facilitate improvement in the speech and swallowing functions of patients with tongue resection or tongue movement disorders. However, a PAP's effect is limited in cases where articulation disorder is severe due to wide glossectomy and/or segmental mandibulectomy. In this paper, we describe speech outcomes of a patient with an articulation disorder following glossectomy and segmental mandibulectomy. We used a palatal plate (PP) based on a PAP, along with an artificial tongue (KAT). Speech improvement was evaluated by a standardized speech intelligibility test consisting of 100 syllables. The speech intelligibility score was significantly higher when the patient wore both the PP and KAT than when he wore neither (p=0.013). The conversational intelligibility score was significantly improved with the PP and KAT than without PP and KAT (p=0.024). These results suggest that speech function can be improved in patients with hard tissue defects with segmental mandibulectomy using both a PP and a KAT. The nature of the design of the PP and that of the KAT will allow these prostheses to address a wide range of tissue defects.

DOI： 10.18926/AMO/54420

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

We propose a spoken dialog strategy for car navigation systems to facilitate safe driving. To drive safely, drivers need to concentrate on their driving; however, their concentration may be disrupted due to disagreement with their spoken dialog system. Therefore, we need to solve the problems of user misunderstandings as well as misunderstanding of spoken dialog systems. For this purpose, we introduced a driver workload level in spoken dialog management in order to prevent user misunderstandings. A key strategy of the dialog management is to make speech redundant if the driver's workload is too high in assuming that the user probably misunderstand the system utterance under such a condition. An experiment was conducted to compare performances of the proposed method and a conventional method using a user simulator. The simulator is developed under the assumption of two types of drivers: an experienced driver model and a novice driver model. Experimental results showed that the proposed strategies achieved better performance than the conventional one for task completion time, task completion rate, and user's positive speech rate. In particular, these performance differences are greater for novice users than for experienced users.

DOI： 10.1109/APSIPA.2015.7415511

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

We propose a method to extract particular sound segments from the sound recorded during the course of a day in order to provide sound segments that can be used to facilitate memory. To extract important parts of the sound data, the proposed method utilizes human behavior based on a multisensing approach. To evaluate the performance of the proposed method, we conducted experiments using sound, acceleration, and global positioning system data collected by five participants for approximately two weeks. The experimental results are summarized as follows: (1) various sounds can be extracted by dividing a day into scenes using the acceleration data; (2) sound recorded in unusual places is preferable to sound recorded in usual places; and (3) speech is preferable to nonspeech sound.

DOI： 10.1007/978-3-319-21380-4_105

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

We propose an algorithm to estimate a person's living area using his/her collected Global Positioning System (GPS) data. The most important feature of the algorithm is the connectivity of places with a home, i.e., a living area must consist of a home, important places, and routes that connect them. This definition is logical because people usually go to a place from home, and there can be several routes to that place. Experimental results show that the proposed algorithm can estimate living area with a precision of 0.82 and recall of 0.86 compared with the grand truth established by users. It is also confirmed that the connectivity of places with a home is necessary to estimate a reasonable living area.

DOI： 10.1007/978-3-319-21383-5_95

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

This paper presents a sound collection system to visualize environmental sounds that are collected using a crowd-sourcing approach. An analysis of physical features is generally used to analyze sound properties
however, human beings not only analyze but also emotionally connect to sounds. If we want to visualize the sounds according to the characteristics of the listener, we need to collect not only the raw sound, but also the subjective feelings associated with them. For this purpose, we developed a sound collection system using a crowdsourcing approach to collect physical sounds, their statistics, and subjective evaluations simultaneously. We then conducted a sound collection experiment using the developed system on ten participants. We collected 6,257 samples of equivalent loudness levels and their locations, and 516 samples of sounds and their locations. Subjective evaluations by the participants are also included in the data. Next, we tried to visualize the sound on a map. The loudness levels are visualized as a color map and the sounds are visualized as icons which indicate the sound type. Finally, we conducted a discrimination experiment on the sound to implement a function of automatic conversion from sounds to appropriate icons. The classifier is trained on the basis of the GMM-UBM (Gaussian Mixture Model and Universal Background Model) method. Experimental results show that the F-measure is 0.52 and the AUC is 0.79.

DOI： 10.1109/PERCOMW.2015.7134069

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper presents an algorithm to mine basic patterns of human activities on a daily basis using non-negative matrix factorization (NMF). The greatest benefit of the algorithm is that it can elicit patterns from which meanings can be easily interpreted. To confirm its performance, the proposed algorithm was applied to PC logging data collected from three occupations in offices. Daily patterns of software usage were extracted for each occupation. Results show that each occupation uses specific software in its own time period, and uses several types of software in parallel in its own combinations. Experiment results also show that patterns of 144 dimension vectors were compressible to those of 11 dimension vectors without degradation in occupation classification performance. Therefore, the proposed algorithm compressed basic software usage patterns to about one-tenth of their original dimensions while preserving the original information. Moreover, the extracted basic patterns showed reasonable interpretation of daily working patterns in offices.

DOI： 10.1109/ICCE.2015.7066309

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ISCA-INT SPEECH COMMUNICATION ASSOC  

As described in this paper, we propose a sub-band speech synthesis approach to develop a high quality Text-to-Speech (TTS) system: a sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated by HMM-based speech synthesis. A key idea is to compensate over-smoothing caused by statistical procedures by introducing a sample-based spectrum, especially in the high-frequency band. Listening test results show that the proposed method has better performance than HMM-based speech synthesis in terms of clarity. It is at the same level as HMM-based speech synthesis in terms of smoothness. In addition, preference test results among the proposed method, HMM-based speech synthesis, and waveform speech synthesis using 80 min speech data reveal that the proposed method is the most liked.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes a sub-band speech synthesis approach to develop high-quality Text-to-Speech (TTS). For the low-frequency band and high-frequency band, Hidden Markov Model (HMM)-based speech synthesis and waveform -based speech synthesis are used, respectively. Both speech synthesis methods are widely known to show good performance and to have benefits and shortcomings from different points of view. One motivation is to apply the right speech synthesis method in the right frequency band. Experiment results show that in terms of the smoothness the proposed approach shows better performance than waveform -based speech synthesis, and in terms of the clarity it shows better than HMM-based speech synthesis. Consequently, the proposed approach combines the inherent benefits from both waveform-based speech synthesis and HMM-based speech synthesis.

DOI： 10.1109/APSIPA.2014.7041575

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

We are striving to develop a new communication technology based on individual experiences that can be extracted from life logs. We have proposed the "Emotion Communication Model" and confirmed that significant correlation exists between experience and emotion. As the second step, particularly addressing impressive places and events, this paper describes an investigation of the extent to which we can share emotional information with others through individuals' experiences. Subjective experiments were conducted using life log data collected during 7-47 months. Experiment results show that (1) impressive places are determined by the distance from home, visit frequency, and direction from home and that (2) positive emotional information is highly consistent among people (71.4%), but it is not true for negative emotional information. Therefore, experiences are useful as metaphors to express positive emotional information.

DOI： 10.1109/PerComW.2014.6815198

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (conference, symposium, etc.)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Language：Japanese   Publishing type：Thesis (other)   Publisher：計測自動制御学会  

CiNii Article

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

In this paper, we propose a system to collect human behavior in detail with higher-level tags such as attitude, accompanying-person, expenditure, tasks and so on. The system makes it possible to construct database to model higher-level human behaviors that are utilized in context-aware services. The system has two input methods
i.e., on-the-fly by a smartphone and post-processing by a PC browser. On the PC, users can interactively know where and when they were, which results in easily and accurately constructing human behavior database. To decrease numbers of operations, users' repetitions and similarity of among users are used. According to experiment results, the system successfully decreases operation time, higher-level tags are properly collected and behavior tendencies of the users are clearly captured. © 2012 Crown Copyright.

DOI： 10.1109/CISIS.2012.81

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ASSOC COMPUTING MACHINERY  

As it is becoming more common for various handheld devices to be equipped with a camera, applications that use image recognition are increasing. Therefore, improving the usability of these devices by enhancing their image capture characteristics is becoming more important. We present ClearPlate - a new optical unit for image capture. It has a physically transparent viewfinder through which the user can observe the target directly without offset; the framed image is captured by the built-in camera. We also present a user study that evaluates ClearPlate performance in the 2D barcode acquisition task. Results show that ClearPlate significantly outperforms the camera-phone-based approach with regard to 2D barcode acquisition.

DOI： 10.1145/1978942.1979346

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

We present ClearPlate-a new optical unit for an image capture device. It has a physically transparent viewfinder through which the user can observe the target directly without offset; the framed image is captured by the built-in camera. We also present a user study that evaluates ClearPlate performance in the 2D code acquisition task. Results show that ClearPlate significantly outperforms the camera-phone-based approach to 2D code acquisition.

DOI： 10.1109/ICCE.2011.5722862

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

In this paper, we propose a method for predicting future locations of a person by exploiting the person's past lifelog data. To predict the future location of a person has many applications such as the delivery of information related to the predicted locations: information with limited lifetimes (sales in a supermarket), weather reports, and traffic reports. Most existing methods for prediction only use historical location data, thus they can only handle regular movements
irregular movements are not considered. Our method predicts future locations by using personal calendar entries in addition to GPS(Global positioning system) data. Using calendar entries makes it possible to predict the locations associated with the irregular events indicated by the entries. We make Dynamic Bayesian Networks models for integrating these different kinds of lifelog data so as to yield better predictions. In experiments on real data, our methods can predict irregular movements successfully even with long lead-times, while matching the accuracy of existing schemes in predicting usual movements. Copyright 2010 ACM.

DOI： 10.1145/1867699.1867702

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

DOI： 10.5715/jnlp.17.4_111

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

We proposed "Twist&Tap" as a new text entry method for TV remotes. The method uses a combination of operations that are easy for the body to remember: multi-tap of the four directional keys and five level twist control of the wrist holding the remote in either clockwise or counterclockwise direction. Experiments confirm that Twist&Tap offers increased text entry speed, and that many of the subjects could achieve text entry speed close to that of the more commonly used Multi-tap interface after just 3 hours of use, in the condition where the users could not see the remote. Twist&Tap is thus an easy-to-learn eyes-free interface.(1).

DOI： 10.1109/TCE.2010.5439140

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

To improve the quality and timeliness of TV program recommendations, a recommendation system that uses life log data such as browsing histories on WEB, locations visited, operation history of consumer electronics, and personal scheduler on PC is proposed. A subjective experiment shows that life log data is effective in improving the quality of program recommendations.

DOI： 10.1109/ICCE.2010.5418741

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

We aim to make it easier and more comfortable to input text via a TV remote control device. Our proposal is a character input method based on detecting the tilt of the device. Users can easily acquire reflex-level typing skills. Experiments confirm the feasibility of the method..

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

DOI： 10.11236/jph.56.11_784

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

We propose a facial color beautification method for video communication. The video-captured Ace often disappoints its, especially the subjects themselves, because the lighting environment is often poor. Inadequate lighting makes the face look depressed or tired. The best solution is illuminating the face directly with good light, but it is, not always possible to realize the perfect environment in everyday situations. Our solution is to retouch the captured video. Our method identifies the distribution of skin color and the eye luminance of a detected face, and converts the color distribution of the entire image by histogram tran formation. This method provides three strong points, which are 1) converting video in real-time, 2) beautifying the facial color even if it is captured under inadequate light, and 3) creating a variety of face "styles" by controlling the transformation parameters. We conduct a computational performace evaluation, which shows that our method provides real-time video processing performance. Moreover, we also conduct a user study to reveal the diversity of user preferences and the method's effectiveness in terms of impression improvement. The user study indicates that our method is effective even though user preferences vary widely.(1)

DOI： 10.1109/TCE.2009.5174466

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In services using lifelog collected continuously and over a long period of time, disclosure control is essential in order to deal with the privacy because this lifelog includes confidential information which users are unwilling to disclose freely. This paper proposes an ontology model for disclosure control needed to handle each user's lifelog. The user is able to easily set disclosure rules on his/her diverse data collected from various data sources. Features of the proposed model are as follows: (1) Values can be differentiated by their context, (2) Various time expressions can be handled and (3) Disclosure attribute is set on each lifelog item (fine-grained control). We show an example of implementation and the result of experiments using an implemented system.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ASSOC COMPUTING MACHINERY  

Television sets and video game consoles equipped with a web browser have appeared, and we are now able to browse web pages on television screens. However, existing navigation techniques are too difficult in this situation. In this paper, we propose Arrow Tag,, a new link selection technique for web browsers on TV. In this technique, sequences of arrow signs called Arrow Tags are assigned to the links of the web pages, so users can select the links by pushing the four direction keys a few times, while keeping her/his gaze fixed on the television screen. User studies show that At-row Tag significantly outperforms the conventional techniques of Focus Move and Number Tag. Moreover, most participants preferred Arrow Tag over either Focus Move or Number Tag.

DOI： 10.1145/1518701.1518857

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

In this paper, we propose a life logger integrated with a remote controller, which is a personal device. It uses several sensors to collect the history of the user's control of consumer appliances as well as his/her actions, stores all data in real time before sending it to PCs or servers, and is small enough to carry at all times. The aim of data integration is to acquire the user's context from his/her actions; personalised services are then provided that suit the context. We develop a prototype and evaluate its performance. The prototype uses Arrow Tags to act as a remote controller for Internet surfing via a TV screen; we designed Arrow Tags to allow the easy selection of any link currently shown by pushing the direction keys, the user can keep his/her gaze fixed on the television screen. Experiments show that Arrow Tag makes it possible for users to easily and comfortably select web page links. To support context mining, the prototype uses our algorithm that can estimate transportation modes from the outputs of GPS and acceleration sensors. Tests show that transportation mode estimation is about 95% accurate. Judging from the experiments results, we can conclude that the life logger, integrated with a remote controller, has the potential to stimulate the development of many context-aware services(1).

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

We aim to provide services that properly take account of the user's interests and/or profile. To achieve this goal, we propose a new device that collects the user's actions and sends them to a PC to be stored as a life log for estimating the user's interests and/or profile. Based on the idea that the user's interaction with consumer electronic appliances provides important information about the user's interests, the device includes a remote controller and several sensors. Experiments show that the device offers good performance both as a remote controller and as a life log collector.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper describes an appliance control system that uses the IDs of the user and the appliances. The system uses knowledge of appliance functionality and the user's need to simplify and unify the control processes performed by the user. Usability experiments conducted on a presentation system show the advantage of the system.

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Image Information and Television Engineers  

we proposed ordinary/unordinary state's label to increase the kind of life log services and to improve the quality of the life log services. We have tried to classify heart rates data to ordinary/unordinary class before. In this paper, we show the results of experiments which we add new characters such as an average of heart rates in a certain window, and time-oriented characters to classify heart rates data with higher accuracy. And we show we classified subjects to two groups. The subjects in one groups, can be esitimated their ordinary/unordinary state from their heart rates. However, we studied the other group's subjects can not be estimated their ordinary/unordinary state from their heart rates. And we observed the case the labeling accuracy getting better with new characters in the case of subjects who can not be estimated their ordinary/unordinary state from their heart rates.

DOI： 10.11485/itetr.33.37.0_91

CiNii Article

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

Tracking the movement of human eyes is expected to yield natural and convenient applications based on human-computer interaction (HCI). To implement an effective eye-tracking system, eye movements must be recorded without placing any restriction on the user's behavior or user discomfort. This paper describes an eye movement recording system that offers free-head, simple configuration. It does not require the user to wear anything on her head, and she can move her head freely. Instead of using a computer, the system uses a visual digital signal processor (DSP) camera to detect the position of eye corner, the center of pupil and then calculate the eye movement. Evaluation tests show that the sampling rate of the system can be 300 Hz and the accuracy is about 1.8 °/s. ©2008 IEEE.

DOI： 10.1109/RIVF.2008.4586369

Scopus

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

This paper proposes a new text to-speech (TTS) system that utilizes large numbers of speech segments to produce very natural and intelligible synthetic speech. There are two innovations; new multiform synthesis units and a new speech modification algorithm based on a vocoder that offers harmonics reconstruction. The multiform units make it possible to reduce acoustic discontinuities at concatenation points and unnatural sound by preparing synthesis units with various lengths and various F-0 contours. The new speech modification algorithm, on the other hand, improves the quality of prosody modified speech. This algorithm is extremely effective in synthesizing speech whose prosodic parameters are quite different from those of synthesis units. Listening tests confirm that the new synthesis units yield speech with high intelligibility and naturalness, and that the new speech modification algorithm is superior to all other conventional vocoders and waveform domain algorithms including TD-PSOLA, especially when modifying the F-0 frequency upward.

DOI： 10.1109/89.890065

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, we propose a new technology that enhances the communication ability of human beings. We call it Action-to-Speech (A2S). A2S generates speech from actions or gestures and makes it possible for people who speak different languages or the speaking impaired to communicate. Features of A2S are as follows. (1) Because meanings are defined by mapping functions between action and speech, it is easy for the system to handle new languages. (2) Because prosodic characteristics of speech can be controlled in real time, smooth communication is possible. (3) Because sensors capture actions, reliable responses are guaranteed. A prototype system was developed. Evaluations indicate that A2S makes it possible for persons speaking different languages to easily and effectively communicate.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes a Computer Assisted Instruction (CAI) system that teaches how to write Japanese characters. The system has two important features: synthesized speech output with the easy generation of various instructions and a Computer Graphics (CG) animated agent that provides a user-friendly interface. The CAI system has a video display tablet interface. A user traces the pattern of a character using the tablet pen, and his/her tracing is shown simultaneously on the display. When the line that the user draws slips outside the pattern, the system simultaneously outputs synthesized speech to correct the error. Evaluation experiments were performed and we confirmed (i) interactive instructions using synthesized speech are effective, (ii) users prefer to receive instructions via both speech and the CG animated agent. (iii) the synthesized speech well matches the CG animated agent.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE COMPUTER SOC  

This paper proposes a new speech modification algorithm which makes it possible to change the fundamental frequency (F-0) while preserving high quality. One novel point of the algorithm is that the spectrum envelope is transformed according to amount of F-0 modification. Based on a codebook mapping formulation, transformation rules are generated using speech data uttered in a different F-0 range. The rules have two purposes: one is transforming the spectrum envelope of the low frequency band and the other is adjusting the balance between low band power and high band power. The proposed algorithm is applied to a text-to-speech system based on waveform concatenation, and good performance is confirmed by listening tests.

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes a new application of speech modification called ''speech morphing''. In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces duces similar results for speech; i.e., one person's speech is gradually changed to that of someone else, Speech morphing makes it possible to create movies or multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency (F-0) and DFT spectrum and outputs high quality speech. To clarify the balance of F-0 modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SCRIPTA TECHNICA-JOHN WILEY & SONS  

When a formant is modified based on the pole of the AR model, a problem arises due to the interaction between the pole to be modified and other poles such as the apparent elimination of the formant, if the frequency of the considered pole simply is modified. To solve this problem, the method proposed in this paper uses the spectral intensity at the pole frequency as a new feature parameter and the spectral intensity at the pole after the frequency modification is corrected to the desired value by iterative processings.
To examine the effectiveness of the proposed method, an experiment was conducted in which a phoneme in a word is replaced into the same phoneme in a different environment, and then the formant frequency is modified by the proposed method in order to restore the original speech. The speeches before and after the modification are compared in terms of the cepstral distance (CD) from the original speech, and it is verified that the proposed method is effective in the modification of the formant. An attempt is made to solve the formant discontinuity problem at the concatenation point in waveform based speech synthesis-by-rule and to modify the formant frequency accompanying the modification of the fundamental frequency using the proposed method. It was verified as a result of experiment that the speech after formant modification is better than the speech before modification, indicating that the proposed method is useful in improving the quality of the synthesized speech.

Web of Science

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

DOI： 10.11477/mf.1662901259

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：ELSEVIER SCIENCE BV  

This article presents a new algorithm used in order to convert the speech of one speaker so that it sounds like that of another speaker. This algorithm flexibly converts voice quality using two major technical developments. Firstly, the modification of formant frequencies and spectral intensity using piecewise linear voice conversion rules. This enables the control of spectrum parameters in detail. The conversion rules are generated automatically for any pair of speakers. The reliability of the conversion rules is guaranteed because they are statistically generated using training data. Secondly, this algorithm provides the ability to produce speech with the desired formant structure by controlling formant frequencies, formant bandwidths and spectral intensity. Speech is iteratively modified in order to achieve the specified formant structure. Listening tests prove that the proposed algorithm converts speaker individuality while maintaining high speech quality.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Web of Science

researchmap

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

DOI： 10.20697/jasj.49.10_682

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

Voice conversion is a technique to change speaker individuality
i.e., speech uttered by a speaker is changed to sound as if another speaker had uttered it. In this paper, we propose a voice conversion algorithm that uses speech segments as conversion units. Input speech is decomposed into speech segments by a speech recognition module and the segments are replaced by speech segments uttered by another speaker. This algorithm makes it possible to convert not only the static characteristics but also speaker individuality contained in phoneme segments. The proposed voice conversion algorithm was performed between two male speakers. Spectrum distortion between target speech and the converted speech was reduced to one-third the natural spectrum difference between the two speakers. A litening experiment showed that, in terms of speaker identification accuracy, the speech converted by segment-sized units gave a score 20% higher than the speech converted frame-by-frame. © 1992, Acoustical Society of Japan. All rights reserved.

DOI： 10.1250/ast.13.131

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：AMER INST PHYSICS  

The goal of cross-language voice conversion is to preserve the speech characteristics of one speaker when that speaker's speech is translated and used to synthesize speech in another language. In this paper, two preliminary studies, i.e., a statistical analysis of spectrum differences in different languages and the first attempt at a cross-language voice conversion, are reported. Speech uttered by a bilingual speaker is analyzed to examine spectrum difference between English and Japanese. Experimental results are (1) the codebook size for mixed speech from English and Japanese should be almost twice the codebook size of either English or Japanese; (2) although many code vectors occurred in both English and Japanese, some have a tendency to predominate in one language or the other; (3) code vectors that predominantly occurred in English are contained in the phonemes /r/, /ae/, /f/, /s/, and code vectors that predominantly occurred in Japanese are contained in /i/, /u/, /N/; and (4) judged from listening tests, listeners cannot reliably indicate the distinction between English speech decoded by a Japanese codebook and English speech decoded by an English codebook. A voice conversion algorithm based on codebook mapping was applied to cross-language voice conversion, and its performance was somewhat less effective than for voice conversion in the same language.

DOI： 10.1121/1.402284

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

researchmap

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese   Publishing type：Research paper, summary (national, other academic conference)  

researchmap

Language：Japanese  

J-GLOBAL

researchmap

researchmap

Language：Japanese  

J-GLOBAL

researchmap

DOI： 10.2186/ajps.9.186

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：(公社)日本歯科医師会  

J-GLOBAL

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人日本機械学会  

There are many lifelog researches to give services with personal daily digitized information.. To realize lifelog services, the labeling technology to enormous quantity of information is necessary. In this paper, we propose a versatile labeling technology focused on the unordinary/ordinary situation of daily life. Our approach regards the difference of data distribution collected in each action. And based on the time-oriented features of the data, we brought in smoothing process, and label-modify-process. We evaluated the accuracy of our approach with heart rate sensor data. The evaluation was conducted on three subjects. Then, we comfirmed more 13.5 % accuracy improvement with above two processes, than without them.

CiNii Article

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

CiNii Article

researchmap

Language：Japanese  

CiNii Article

J-GLOBAL

researchmap

Language：Japanese  

CiNii Article

J-GLOBAL

researchmap

Language：Japanese  

CiNii Article

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

There are many lifelog researches to give services with personal daily digitized information.. To realize lifelog services, the labeling technology to enormous quantity of information is necessary. In this paper, we propose a versatile labeling technology focused on the unordinary/ordinary situation of daily life. At first, we evaluate the difference of data distribution collected in each action, the influence of the circadian change, and the accuracy of our approach with heart rate sensor data. Then, we analized the time-oriented features of the result. And based on this analysis, we brought in smoothing process, and label-modify-process. Then, we comfirmed more than 20% accuracy improvement.

CiNii Article

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人情報処理学会  

In this report, we propose a method for extracting movement patterns of a person from location data obtained by carrying a GPS data logger. First we translate GPS data to a discrete sequence by aligning the places the user had stayed in time series order, then we use sequential frequent pattern mining technique and obtain frequent movement patterns. Moreover, we propose three methods to select feature movement patterns from those mined ones. We evaluate these methods by applying representative movement patterns to location data from GPS and show features of each method.

CiNii Article

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

In recent years, because of miniaturization of mobile terminals with various sensors, life-log services have begun to realize. However, life-log data includes information users do not want not to disclose. Therefore, a life-log management system must provide users' life-logs to service providers without anxiety of users. In this report, we propose a life-log system which users can manage their life-logs in their local equipments, PCs or home servers. The system can provide a sense of security for its users. And in the life log system, the users decide whether they disclose their life log or not, when they want to get the services. In this study, we focus on clarifying life-logs disclosed to service providers in order to decline users' anxiety. And, we mentioned the concept of visualizing life-logs and supporting users' decision for disclosing their life-logs to several services. Finally, we report the prototype system implemented based on this concept.

CiNii Article

researchmap

Language：Japanese   Publisher：一般社団法人情報処理学会  

In recent years, positional measurement products using GPS, Wifi signal or other sensors has become familiar, and users can easily record there location information. Moving tracks using location data is one of the most fundamental information in life-log. Location data can be combined with various data, such as purchase histories, attention histories, or photographs. While current context awareness services simply use customer's locations, user's behavioral traits or life style estimated from location data are more variable. While current services only use user's location, more variable services can be provided using user's behavioral trait and lifestyle which can be estimate by user's life-log. Our research aims to estimate user's situation and their profile from accumulated location data. In this paper, we examine the method of extracting activity modes, that is, moving or staying, from positional histories.

CiNii Article

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人情報処理学会  

In this paper, we propose the method for increasing precision of the accompanied level using location data form GPS or WiFi equipments. A margin of error in location data cause misjudgments in accompaniment. Therefore, there is problem that these data is not in the right place. We propose a way using margin of error to solve the problem and demonstrate effectiveness of our approach with empirical results.

CiNii Article

J-GLOBAL

researchmap

Language：Japanese  

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

In recent years, it has become familiar a positional measurement such as GPS, and users can easily record there location information. The location data which include moving tracks is the most basic data in life-log. The location data can be combined with various data, purchase histories, attention histories, photographs, and so on. Those data attempt to use for life-log service. While current services only use user's location, more variable services can be provided using user's behavioral trait and lifestyle which can be estimate by user's life-log. Our research aims to estimate user's situation and their profile from accumulated location data. In this paper, we examine the method of extracting activity modes, that is moving or staying, from positional histories.

CiNii Article

J-GLOBAL

researchmap

Language：Japanese   Publisher：一般社団法人電子情報通信学会  

We report functional enhancement of the "Merurobo Digital Log System": a network-based interactive child-watch system for nurseries. This system consists of the "Action Switch Platform" which links the PaPeRo (Partner-type Personal Robot) to cellular phones of the parents and a controller used by the nursery teacher. Additional functions include service sets which are automatically switched according to the estimated contexts of the teacher. Teacher's activities are collected by local sensors in real-time and the PaPeRo is driven by the current service set. We implement the service set switching function and assess the integrated system in a nursery facility. Finally, we report efficiency of the context based service switching and the asynchronous communication model with robot interface by analyzing the teacher's actions and comments.

CiNii Article

J-GLOBAL

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese  

researchmap

Language：Japanese  

researchmap

Language：Japanese  

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Language：English   Publisher：NTT CORP  

There is a marked difference between speech heard in direct face-to-face conversation and speech heard over the telephone. A good example is provided by an FM radio broadcast when a listener calls in to chat with the disk jockey on the air. This disparity in quality led us to develop an algorithm of generating wideband speech from ordinary telephone speech. The algorithm has two novel points. The first is spectrum envelope reconstruction based on codebook mapping. The other is speech signal reconstruction using the speech waveform specified by the reconstructed spectrum envelope. Because the algorithm makes if possible to generate high quality speech without the use of any additional transmitted information, if is important and useful in the area of speech coding. Evaluation by the acoustic distance measure and by listening tests confirmed the good performance of the algorithm.

Web of Science

researchmap

DOI： 10.20697/jasj.51.11_882

researchmap

researchmap

Language：Japanese  

J-GLOBAL

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Country：Japan

researchmap

Country：Japan

researchmap

Country：Japan

researchmap