研究者詳細 - 阿部　匡伸

論文 - 阿部　匡伸

分割表示 117 件中 81 - 100 件目／全件表示 >>

Development of CAI system employing synthesized speech and CG animated agent 査読

T Shinozaki, M Abe

2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III 585 - 588 2000年8月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：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

WebMessenger: A new framework to produce multimedia content by combining synthesized speech and moving pictures in the WWW environment 査読

M. Abe, H. Mizuno, T. Shinozaki

Proc. Multimedia Signal Processing (MMSP)'99 611 - 616 1999年9月

A Japanese Text-to-Speech system based on multi-from units with consideration of frequency distribution in Japanese 査読

K. Tanaka, H. Mizuno, M. Abe, S. Nakajima

Proc. European Conf. on Speech Communication and Technology (EuroSpeech)'99 389 - 392 1999年9月

A new F0 modification algorithm by manipulating harmonics of magnitude spectrum 査読

S. Takano, M. Abe

Proc. European Conf. on Speech Communication and Technology (EuroSpeech)'99 1875 - 1878 1999年9月

Development of speech design tool 'Sesign99' to enhance synthesized speech 査読

H. Mizuno, M. Abe, S. Nakajim

Proc. European Conf. on Speech Communication and Technology (EuroSpeech)'99 2083 - 2086 1999年9月

A development of CAI system employing synthesized speech responses 査読

T. Shinozaki, M. Abe

Int. Conf. on Spoken Language Processing (ICSLP) '98 2855 - 2858 1998年12月

Report on the Third ESCA TTS Workshop Evaluation Procedure 査読

J. Santan, L.Pols, M. Abe, D. Kahn, E. Keller, J. Vonwiller

3rd Int. Workshop on Speech Synthesis 329 - 332 1998年11月

The use of large text corpora for evaluating text-to-speech systems 査読

L.Pols, J. Santan, M. Abe, D. Kahn, E.Keller

1st Int. Conf. on Language Research and Evaluation 421 - 424 1998年5月

A prototype hybrid scalable text-to-speech system 査読

M. Abe, H. Mizuno, S. Takahashi, S. Nakajima

Proc. Workshop on Synthetic Natural Hybrid Coding(SNHC) and 3D Image 8 - 11 1997年9月

A new framework to provide high-controllability speech signal and the development of a workbench for it 査読

M. Abe, H. Mizuno, S. Takahashi, S. Nakajima

Proc. European Conf. on Speech Communication and Technology (EuroSpeech)'97 541 - 544 1997年9月

A new fundamental frequency modification algorithm with transformation of spectrum envelope according to F-0 査読

K Tanaka, M Abe

1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V 951 - 954 1997年5月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：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

誤り指示音声の特徴分析と音声出力への適用査読

阿部匡伸

電子情報通信学会論文誌. D-II J79-D-II ( 12 ) 2191 - 2198 1996年12月

Speech morphing by gradually changing spectrum parameter and fundamental frequency 査読

M Abe

ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 2235 - 2238 1996年10月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）出版者・発行元：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

An information retrieval system from text database using text-to-speech 査読

M. Abe, K. Hakoda, H. Tsukada

Applied Voice Input/Output Society (AVIOS)'96 189 - 196 1996年9月

A formant frequency modification algorithm dealing with the pole interaction 査読

H Mizuno, M Abe

ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 79 ( 1 ) 46 - 55 1996年1月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：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

異なる発話様式の特徴分析とその制御査読

阿部匡伸

日本音響学会誌 51 ( 12 ) 929 - 937 1995年12月

Analysis of prosodic characteristics in speech advisories and their application to speech output 査読

M. Abe

Proc. European Conf. on Speech Communication and Technology (EuroSpeech)'95 2031 - 2034 1995年9月

Using speech advisories to correct human errors; Human speech vs. Synthetic speech 査読

M. Abe

Proc. Human Computer Interaction (HCI)'95 61 - 61 1995年6月

極相互の相関を考慮したフォルマント周波数変換法査読

水野秀之, 阿部匡伸

電子情報通信学会論文誌. A J78-A ( 3 ) 287 - 294 1995年3月

VOICE CONVERSION ALGORITHM-BASED ON PIECEWISE-LINEAR CONVERSION RULES OF FORMANT FREQUENCY AND SPECTRUM TILT

H MIZUNO, M ABE

SPEECH COMMUNICATION 16 ( 2 ) 153 - 164 1995年2月

記述言語：英語掲載種別：研究論文（学術雑誌）出版者・発行元：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

　前のページ - 次のページ　

<阿部 匡伸>

論文 - 阿部 匡伸

<阿部　匡伸>

論文 - 阿部　匡伸