Faculty Profiles - HARA Sunao

Papers - HARA Sunao

Division display 41 - 60 of about 62 ／ All the affair displays >>

New approach to emotional information exchange: Experience metaphor based on life logs Reviewed International journal

Masanobu Abe, Daisuke Fujioka, Kazuto Hamano, Sunao Hara, Rika Mochizuki, Tomoki Watanabe

2014 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom 2014 Workshops 191 - 194 2014.3

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

researchmap

Development of a Toolkit Handling Multiple Speech-Oriented Guidance Agents for Mobile Applications Reviewed International journal

Sunao Hara, Hiromichi Kawanami, Hiroshi Saruwatari, Kiyohiro Shikano

Natural Interaction with Robots, Knowbots and Smartphones, Putting Spoken Dialog Systems into Practice 79 - 85 2014

Evaluation of Invalid Input Discrimination Using Bag-of-Words for Speech-Oriented Guidance System Reviewed International journal

Haruka Majima, Rafael Torres, Hiromichi Kawanami, Sunao Hara, Tomoko Matsui, Hiroshi Saruwatari, Kiyohiro Shikano

Natural Interaction with Robots, Knowbots and Smartphones, Putting Spoken Dialog Systems into Practice 389 - 397 2014

A Hybrid Text-to-Speech Based on Sub-Band Approach Reviewed International journal

Takuma Inoue, Sunao Hara, Masanobu Abe

Proceedings of Asia-Pacific Signal and Information Processing Association 2014 Annual Summit and Conference 1 - 4 2014

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

Invalid Input Rejection Using Bag-of-Words for Speech-oriented Guidance System Reviewed

Haruka Majima, Yoko Fujita, Rafael Torres, Hiromichi Kawanami, Sunao Hara, Tomoko Matsui, Hiroshi Saruwatari, Kiyohiro Shikano

Journal of Information Processing 54 ( 2 ) 443 - 451 2013.2

Language：Japanese

On a real environment speech-oriented information guidance system, a valid and invalid input discrimination is important as invalid inputs such as noise, laugh, cough and utterances between users lead to unpredictable system responses. Generally, acoustic features such as MFCC (Mel-Frequency Cepstral Coefficient) are used for discrimination. Comparing acoustic likelihoods of GMMs (Gaussian Mixture Models) from speech data and noise data is one of the typical methods. In addition to that, using linguistic features, such as speech recognition result, is considered to improve discrimination accuracy as it reflects the task-domain of invalid inputs and meaningless recognition results from noise inputs. In this paper, we introduce Bag-of-Words (BOW) as a feature to discriminate between valid and invalid inputs. Support Vector Machine (SVM) and Maximum Entropy method (ME) are also employed to realize robust classification. We experimented the methods using real environment data obtained from the guidance system "Takemaru-kun." By applying BOW on SVM, the F-measure is improved to 85.09%, from 82.19% when using GMMs. In addition, experiments using features combining BOW with acoustic likelihoods from GMMs, Duration and SNR were conducted, improving the F-measure to 86.58%.

CiNii Article

CiNii Books

researchmap

On-line detection of task incompletion for spoken dialog systems based on utterance and behavior tag N-gram Reviewed

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

The IEICE Transactions on Information and Systems (Japanese edition) J96-D ( 1 ) 81 - 93 2013.1

Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition Reviewed

Arata Itoh, Sunao Hara, Norihide Kitaoka, Kazuya Takeda

IEICE TRANSACTIONS on Information and Systems E95D ( 10 ) 2479 - 2485 2012.10

Language：English Publishing type：Research paper (scientific journal) Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG

A novel speech feature generation-based acoustic model training method for robust speaker-independent speech recognition is proposed. For decades, speaker adaptation methods have been widely used. All of these adaptation methods need adaptation data. However, our proposed method aims to create speaker-independent acoustic models that cover not only known but also unknown speakers. We achieve this by adopting inverse maximum likelihood linear regression (MLLR) transformation-based feature generation, and then we train our models using these features. First we obtain MLLR transformation matrices from a limited number of existing speakers. Then we extract the bases of the MLLR transformation matrices using PCA. The distribution of the weight parameters to express the transformation matrices for the existing speakers are estimated. Next, we construct pseudo-speaker transformations by sampling the weight parameters from the distribution, and apply the transformation to the normalized features of the existing speaker to generate the features of the pseudo-speakers. Finally, using these features, we train the acoustic models. Evaluation results show that the acoustic models trained using our proposed method are robust for unknown speakers.

DOI： 10.1587/transinf.E95.D.2479

Web of Science

researchmap

Other Link： http://search.ieice.org/bin/summary.php?id=e95-d_10_2479

Causal analysis of task completion errors in spoken music retrieval interactions Reviewed International journal

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of the 8th international conference on Language Resources and Evaluation (LREC 2012) 1365 - 1372 2012.5

Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：EUROPEAN LANGUAGE RESOURCES ASSOC-ELRA

In this paper, we analyze the causes of task completion errors in spoken dialog systems, using a decision tree with N-gram features of the dialog to detect task-incomplete dialogs. The dialog for a music retrieval task is described by a sequence of tags related to user and system utterances and behaviors. The dialogs are manually classified into two classes: completed and uncompleted music retrieval tasks. Differences in tag classification performance between the two classes are discussed. We then construct decision trees which can detect if a dialog finished with the task completed or not, using information gain criterion. Decision trees using N-grams of manual tags and automatic tags achieved 74.2% and 80.4% classification accuracy, respectively, while the tree using interaction parameters achieved an accuracy rate of 65.7%. We also discuss more details of the causality of task incompletion for spoken dialog systems using such trees.

Web of Science

researchmap

Other Link： http://www.lrec-conf.org/proceedings/lrec2012/summaries/1059.html

Robust seed model training for speaker adaptation using pseudo-speaker features generated by inverse CMLLR transformation Reviewed International journal

Arata Itoh, Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of 2011 Automatic Speech Recognition and Understanding Workshop (ASRU 2011) 169 - 172 2011.12

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

In this paper, we propose a novel acoustic model training method which is suitable for speaker adaptation in speech recognition. Our method is based on feature generation from a small amount of speakers' data. For decades, speaker adaptation methods have been widely used. Such adaptation methods need some amount of adaptation data and if the data is not sufficient, speech recognition performance degrade significantly. If the seed models to be adapted to a specific speaker can widely cover more speakers, speaker adaptation can perform robustly. To make such robust seed models, we adopt inverse maximum likelihood linear regression (MLLR) transformation-based feature generation, and then train our seed models using these features. First we obtain MLLR transformation matrices from a limited number of existing speakers. Then we extract the bases of the MLLR transformation matrices using PCA. The distribution of the weight parameters to express the MLLR transformation matrices for the existing speakers is estimated. Next we generate pseudo-speaker MLLR transformations by sampling the weight parameters from the distribution, and apply the inverse of the transformation to the normalized existing speaker features to generate the pseudo-speakers' features. Finally, using these features, we train the acoustic seed models. Using this seed models, we obtained better speaker adaptation results than using simply environmentally adapted models. © 2011 IEEE.

DOI： 10.1109/ASRU.2011.6163925

Scopus

researchmap

Training Robust Acoustic Models Using Features of Pseudo-Speakers Generated by Inverse CMLLR Transformations Reviewed International journal

Arata Itoh, Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of 2011 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2011) 1 - 5 2011.12

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

In this paper a novel speech feature generationbased acoustic model training method is proposed. For decades, speaker adaptation methods have been widely used. All existing adaptation methods need adaptation data. However, our proposed method creates speaker-independent acoustic models that cover not only known but also unknown speakers. We do this by adopting inverse maximum likelihood linear regression (MLLR) transformation-based feature generation, and then train our models using these features. First we obtain MLLR transformation matrices from a limited number of existing speakers. Then we extract the bases of the MLLR transformation matrices using PCA. The distribution of the weight parameters to express the MLLR transformation matrices for the existing speakers are estimated. Next we generate pseudo-speaker MLLR transformations by sampling the weight parameters from the distribution, and apply the inverse of the transformation to the normalized existing speaker features to generate the pseudospeakers' features. Finally, using these features, we train the acoustic models. Evaluation results show that the acoustic models which are created are robust for unknown speakers.

Scopus

researchmap

On-line detection of task incompletion for spoken dialog systems using utterance and behavior tag N-gram vectors Reviewed International journal

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of the Paralinguistic Information and Its Integration in Spoken Dialogue Systems Workshop 215 - 225 2011.9

Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems Reviewed International journal

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of INTERSPEECH 2011 1312 - 1315 2011

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

We propose a method of detecting "task incomplete" dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Off-line and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.

Web of Science

researchmap

Other Link： http://www.isca-speech.org/archive/interspeech_2011/i11_1305.html

Music Recommendation System Based on Human-to-human Conversation Recognition Reviewed International journal

Hiromasa Ohashi, Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Workshop Proceedings of the 7th International Conference on Intelligent Environments: Ambient Intelligence and Smart Environments 10 352 - 361 2011

Language：English Publishing type：Part of collection (book) Publisher：IOS PRESS

We developed an ambient system that plays music suitable for the mood of a human-human conversation using words obtained from a continuous-speech recognition system. Using the correspondence between a document space based on the texts related to the music and an acoustic space that expresses various audio features, the continuous-speech recognition results are mapped to an acoustic space. We performed a subjective evaluation of the system. The subjects rated the recommended music and the result reveals that the 10 most highly recommended selections included suitable music.

DOI： 10.3233/978-1-60750-795-6-352

Web of Science

researchmap

Automatic detection of task-incompleted dialog for spoken dialog system based on dialog act N-gram Reviewed International journal

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of INTERSPEECH2010 3034 - 3037 2010.9

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

In this paper, we propose a method of detecting task-incompleted users for a spoken dialog system using an N-gram-based dialog history model. We collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database was made by a field test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model was trained from sequences that consist of user dialog acts and/or system dialog acts for two dialog classes, that is, the dialog completed the music retrieval task or the dialog incompleted the task. Then the system detects unknown dialogs that is not completed the task based on the N-gram likelihood. Experiments were conducted on large real data, and the results show that our proposed method achieved good classification performance. When the classifier correctly detected all of the task-incompleted dialogs, our proposed method achieved a false detection rate of 6%.

Web of Science

researchmap

Other Link： http://www.isca-speech.org/archive/interspeech_2010/i10_3034.html

Rapid acoustic model adaptation using inverse MLLR-based feature generation Reviewed International journal

Arata Ito, Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Proceedings of ICA2010 5 1 - 6 2010.8

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

We propose a technique for generating a large amount of target speaker-like speech features by converting a large amount of prepared speech features of many speakers into features similar to those of the target speaker using a transformation matrix. To generate a large amount of target speaker-like features, the system only needs a very small amount of the target speaker's utterances. This technique enables the system to adapt the acoustic model efficiently from a small amount of the target speaker's utterances. To evaluate the proposed method, we prepared 100 reference speakers and 12 target (test) speakers. We conducted the experiments in an isolated word recognition task using a speech database collected by real PC-based distributed environments and compared our proposed method with MLLR, MAP and the method theoretically equivalent to the SAT. Experimental results proved that the proposed method needed a significantly smaller amount of the target speaker's utterances than conventional MLLR, MAP and SAT.

Scopus

researchmap

Estimation method of user satisfaction using N-gram-based dialog history model for spoken dialog system Reviewed International journal

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

LREC 2010 - SEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION 78 - 83 2010.5

Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings) Publisher：EUROPEAN LANGUAGE RESOURCES ASSOC-ELRA

In this paper, we propose an estimation method of user satisfaction for a spoken dialog system using an N-gram-based dialog history model. We have collected a large amount of spoken dialog data accompanied by usability evaluation scores by users in real environments. The database is made by a field-test in which naive users used a client-server music retrieval system with a spoken dialog interface on their own PCs. An N-gram model is trained from the sequences that consist of users' dialog acts and/or the system's dialog acts for each one of six user satisfaction levels: from 1 to 5 and phi (task not completed). Then, the satisfaction level is estimated based on the N-gram likelihood. Experiments were conducted on the large real data and the results show that our proposed method achieved good classification performance; the classification accuracy was 94.7% in the experiment on a classification into dialogs with task completion and those without task completion. Even if the classifier detected all of the task incomplete dialog correctly, our proposed method achieved the false detection rate of only 6%.

Web of Science

researchmap

Other Link： http://www.lrec-conf.org/proceedings/lrec2010/summaries/579.html

Data collection and usability study of a PC-based speech application in various user environments Reviewed International journal

Sunao Hara, Chiyomi Miyajima, Katsunobu Ito, Norihide Kitaoka, Kazuya Takeda

Proceedings of Oriental-COCOSDA 2008 39 - 44 2008.11

In-car Speech Data Collection along with Various Multimodal Signals Reviewed International journal

Akira Ozaki, Sunao Hara, Takashi Kusakawa, Chiyomi Miyajima, Takanori Nishino, Norihide Kitaoka, Katunobu Itou, Kazuya Takeda

Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08) 1846 - 1851 2008.5

Language：English Publishing type：Research paper (international conference proceedings) Publisher：EUROPEAN LANGUAGE RESOURCES ASSOC-ELRA

In this paper, a large-scale real-world speech database is introduced along with other multimedia driving data. We designed a data collection vehicle equipped with various sensors to synchronously record twelve-channel speech, three-channel video, driving behavior including gas and brake pedal pressures, steering angles, and vehicle velocities, physiological signals including driver heart rate, skin conductance, and emotion-based sweating on the palms and soles, etc. These multimodal data are collected while driving on city streets and expressways under four different driving task conditions including two kinds of monologues, human-human dialog, and human-machine dialog. We investigated the response timing of drivers against navigator utterances and found that most overlapped with the preceding utterance due to the task characteristics and the features of Japanese. When comparing utterance length, speaking rate, and the filler rate of driver utterances in human-human and human-machine dialogs, we found that drivers tended to use longer and faster utterances with more fillers to talk with humans than machines.

Web of Science

researchmap

Other Link： http://www.lrec-conf.org/proceedings/lrec2008/summaries/472.html

Data Collection System for the Speech Utterances to an Automatic Speech Recognition System under Real Environments Reviewed

Sunao Hara, Chiyomi Miyajima, Katsunobu Itou, Kazuya Takeda

The IEICE transactions on information and systems J90-D ( 10 ) 2807 - 2816 2007.10

An online customizable music retrieval system with a spoken dialogue interface Reviewed International journal

Sunao Hara, Chiyomi Miyajima, Katsunobu Itou, Kazuya Takeda

The Journal of the Acoustical Society of America 120 ( 5-2 ) 3378 - 3379 2006.11

　 PREV - NEXT 　

< HARA Sunao >

Papers - HARA Sunao