国際会議発表論文 (International Conference Papers)
(Reviewed 査読のあるもの。発表時期逆順。2003年1月現在)
- [Takeda2004ISMIR10] (音楽情報処理)
Haruto TAKEDA, Takuya Nishimoto, Shigeki Sagayama, ``Rhythm and Tempo Recognition of Music Performance from a Probabilistic Approach," Proc. 5th International Conference on Music Information Retrieval (ISMIR) (Barcelona, Spain), pp.357-364, Oct. 2004. [PDF file (388kB)]
- [Kameoka2004ICSLP10] (音声信号処理)
Hirokazu Kameoka, Takuya Nishimoto, Shigeki Sagayama, ``Multi-Pitch Trajectory Estimation of Concurrent Speech Based on Harmonic GMM and Nonlinear Kalman Filtering," Proc. International Conference on Spoken Language Processing (ICSLP2004) (Jeju, Korea), Oct. 2004. [PDF file (190kB)]
- [Sagayama2004ICSLP10] (音響信号処理)
Shigeki Sagayama, Takashi Okajima, Yutaka Kamamoto, Takuya Nishimoto, ``Complex Spectrum Circle Centroid for Microphone-Array-Based Noisy Speech Recognition," Proc. International Conference on Spoken Language Processing (ICSLP2004) (Jeju, Korea), Oct. 2004. [PDF file (125kB)]
- [Raut2004ICSLP10] (音声認識)
Chandra Kant Raut, Takuya Nishimoto, Shigeki Sagayama, ``Model Composition by Lagrange Polynomial Approximation for Robust Speech Recognition in Noisy Environment,'' Proc. International Conference on Spoken Language Processing (ICSLP2004) (Jeju, Korea), Oct. 2004. [PDF file (146kB)]
- [Sagayama2004SAPA10] (音楽信号処理)
Shigeki Sagayama, Hirokazu Kameoka, Takuya Nishimoto, ``Specmurt Anasylis: A Piano-Roll-Visualization of Polyphonic Music Signal by Deconvolution of Log-Frequency Spectrum,'' Proc. 2004 ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing (SAPA2004), (2 October 2004 - 3 October 2004, Jeju, Korea), Oct. 2004. [PDF file (570kB)]
- [Kameoka2004ICASSP05] (音楽信号処理)
Hirokazu Kameoka, Takuya Nishimoto, Shigeki Sagayama: ``Separation of Harmonic Structures Based on Tied Gaussian Mixture Model and Information Criterion for Concurrent Sounds,'' Proc. IEEE, International Conference on Acoustics, Speech and Signal Processing (ICASSP 2004) (Montreal, Canada), May 2004. [PDF file (127kB)]
- [Kameoka2004ICA04] (音楽信号処理)
Hirokazu Kameoka, Takuya Nishimoto, and Shigeki Sagayama, ``Extraction of Multiple Fundamental Frequencies from Polyphonic Music Using Harmonic Clustering,'' Proc. International Congress on Acoustics (ICA) (Kyoto, Japan), Apr. 2004. [PDF file (1557kB)]
- [Takeda2004ISMA03] (音楽情報処理)
Haruto Takeda, Takuya Nishimoto, Shigeki Sagayama, ``Maximum Likelihood Method for Estimating Rhythm and Tempo,'' Proc. International Symposium on Music Acoustics (ISMA) (Nara, Japan), in CD-ROM, Mar. 2004. [PDF file (155kB)]
- [Kameoka2004SP03] (音声信号処理)
Hirokazu Kameoka, Takuya Nishimoto, and Shigeki Sagayama, ``Multi-pitch Detection Algorithm Using Constrained Gaussian Mixture Model and Information Criterion,'' Proc. Speech Prosody 2004 (Nara, Japan), pp.533-536, Mar. 2004. [PDF file (215kB)]
- [Kameoka2004ICASSP]
Hirokazu Kameoka, Takuya Nishimoto and Shigeki Sagayama,
``Separation of Harmonic Structures Based on Tied Gaussian
Mixture Model and Information Criterion for Concurrent
Sounds,'' Proc. IEEE, International Conference on
Acoustics, Speech and Signal Processing (ICASSP2004), to appear in May 2004.
- [Kameoka2004ICA]
Hirokazu Kameoka, Takuya Nishimoto and Shigeki Sagayama,
``Extraction of Multiple Fundamental Frequencies from
Polyphonic Music Using Harmonic Clustering,''
Proc. 18th International Congress on Acoustics, to appear in Apr 2004.
- [Kameoka2004SP]
Hirokazu Kameoka, Takuya Nishimoto and Shigeki Sagayama,
``Multi-pitch Detection Algorithm Using Constrained
Gaussian Mixture Model and Information Criterion for
Simultaneous Speech,'' Proc. Speech Prosody 2004}, to appear in Mar 2004.
- [Kameoka2004SWIM01] (音声信号処理)
Hirokazu Kameoka, Takuya Nishimoto and Shigeki Sagayama, ``Accurate F0 Detection Algorithm for Concurrent Sounds Based on EM Algorithm and Information Criterion,'' Proc. Special Workshop in Maui (SWIM) (Maui, USA) in CD-ROM, Jan. 2004. [PDF file (202kB)]
- [Yamamoto2004SWIM01] (音声認識)
Hitoshi Yamamoto, Takuya Nishimoto and Shigeki Sagayama, ``Frame-by-frame HMM Adaptation for Reverberant Speech Recognition,'' Proc. Special Workshop in Maui (SWIM) (Maui, USA) in CD-ROM, Jan. 2004. [PDF file (136kB)]
- [Takeda2003ISMIR10]
Haruto Takeda, Takuya Nishimoto, Shigeki Sagayama: ``Automatic Rhythm Transcription from Multiphonic MIDI Signals,'' Proc. 4th International Conference on Music Information Retrieval (ISMIR) (Baltimore, USA), Proc. ISMIR 2003, pp.263-264, Oct. 2003. [PDF file (868kB)]
- [Shimodaira2003ICDAR]
Hiroshi Shimodaira, Takashi Sudo, Mitsuru Nakai, Shigeki Sagayama, ``On-line Overlaid-Handwriting Recognition Based on Substroke HMMs,'' ICDAR'03, pp.1043-1047, Aug 2003.
- [Nakai2003ICDAR]
Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama, ``Generation of Hierarchical Dictionary for Stroke-order Free Kanji Handwriting Recognition Based on Substroke HMM,'' Proc. of ICDAR2003, pp.514-518, Aug 2003.
- [Tokuno2003HCII]
Tokuno Junko, Naoto Akira, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama, ``Blind-handwriting Interface for Wearable Computing,'' Proc. of Human - Computer Interaction (HCI) International 2003, Volume 2, pp.303-307, Jun 2003.
- [Takeda2002MMSP12]
Haruto Takeda, Naoki Saito, Tomoshi Otsuki, Mitsuru Nakai, Hiroshi
Shimodaira, Shigeki Sagayama, ``Hidden Markov Model
for Automatic Transcription of MIDI Signals,'' Proc. IEEE Workshop on
Multimedia Signal Processing (US Vigin Islands), Dec 2002.
- [Kawamoto2002PRICAI]
Shin-ichi Kawamoto, Hiroshi Shimodaira, Tsuneo Nitta, Takuya
Nishimoto, Satoshi Nakamura, Katsunobu Itou, Shigeo Morishima, Tatsuo
Yotsukura, Atsuhiko Kai, Akinobu Lee, Yoichi Yamashita, Takao
Kobayashi, Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, Atsushi
Yamada, Yasuharu Den, Takehito Utsuro, Shigeki Sagayama, ``Open-source
software for developing anthropomorphic spoken dialog agent,''
Proc. of PRICAI-02, International Workshop on Lifelike Animated
Agents, pp.64-69, Aug. 2002.
- [Nakai2002ICPR]
Mitsuru Nakai, T. Sudo, Hiroshi Shimodaira, Shigeki Sagayama: ``Pen
Pressure Features for Writer-Independent On-Line Handwriting
Recognition Based on Substroke HMM,'' Proc. Int. Conf. on Pattern
Recognition (ICPR2002), Vol. III, pp. 220-223, Aug. 2002.
- [Tokuno2002IWFHR]
Junko Tokuno, Nobuhito Inami, Shigeki Matsuda, Mitsuru Nakai, Hiroshi
Shimodaira, Shigeki Sagayama: ``Context-Dependent Substroke Model for
HMM-based On-line Handwriting Recognition,'' Proc. Int. Workshop on
Frontiers of Handwriting Recognition (IWFHR-8), Aug. 2002.
- [Shimodaira2002ICASSP]
Hiroshi Shimodaira, Nobuyoshi Sakai, Mitsuru Nakai, Shigeki Sagayama,
``Jacobian Joint Adaptation to Noise, Channel and Vocal Tract Length,''
Proc. of ICASSP2002 (Orlando, USA),
May 2002.
- [Shimodaira2001NIPS]
Hiroshi Shimodaira, Ken-ichi Noma, Mitsuru Nakai, Shigeki Sagayama,
``Dynamic Time-Alignment Kernel in Support Vector Machine,''
NIPS2001 (Neural Information Processing Systems Natural and Synthetic),
Dec 2001.
(
[postscript file (111KB)])
- [Shimodaira2001Eurospeech09]
Hiroshi Shimodaira, Ken-ichi Noma, Mitsuru Nakai, Shigeki Sagayama,
``Support Vector Machine with Dynamic Time-Alignment Kernel for Speech
Recognition,'' Proc. of Eurospeech 2001, Sep 2001.
- [Nakai2001ICDAR09]
Mitsuru Nakai, Naoto Akira, Hiroshi Shimodaira, Shigeki Sagayama,
``Substroke Approach to HMM-based On-line Kanji Handwriting Recognition,''
Proc. of ICDAR'01,
pp.491-495,
Sep 2001.
- [Sagayama2001ISCA08b] (Invited Paper)
Shigeki Sagayama, Koichi Shinoda, Mitsuru Nakai and Hiroshi
Shimodaira, ``Analytic Methods for Acoustic Model Adaptation: A
Review,'' Proc. ISCA Workshop on Adaptation Methods (Sophia Antipolis,
France), pp. 67--76, Aug. 2001.
[pdf file (265kB) available]
- [Sagayama2001ISCA08a]
Shigeki Sagayama, Yutaka Kato, Mitsuru Nakai and Hiroshi Shimodaira,
``Jacobian Approach to Joint Adaptation to Noise, Channel and Vocal
Tract Length,''
Proc. ISCA Workshop on Adaptation Methods (Sophia Antipolis,
France), pp. 117--120, Aug. 2001.
[pdf file (117kB) available]
- [Fujinaga2001ICASSP05]
Katsuhisa Fujinaga, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki
Sagayama, ``Multiple-Regression Hidden Markov Model,'' Proc. ICASSP
2001, May 2001.
- [Shimodaira2000ICSLP10]
Hiroshi Shimodaira, Toshihiko Akae, Mitsuru Nakai, Shigeki Sagayama,
``Jacobian Adaptation of HMM with Initial Model Selection for Noisy
Speech Recognition,'' Proc. ICSLP2000, pp.1003-1006, Oct 2000.
- [Matsuda2000ICSLP10]
Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama,
``Feature-dependent Allophone Clustering,'' Proc. ICSLP2000,
pp. 413-416, Oct 2000.
- [Matsuda2000ICASSP06]
Shigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira and Shigeki
Sagayama, ``Asynchronous-Transition HMM,'' Proc. ICASSP (Istanbul,
Turkey), Vol. II, pp.1001-1004, Jun 2000.
- [Sagayama2000SLRU02] (Invited Paper)
Shigeki Sagayama, ``A Pessimistic View to Dictation Applications / An
Optimistic View to Dictation Techniology,'' Handout for DARPA/Bell
Labs Workshop on Spoken Language Recognition and Understanding 2000
(New Jersey, USA), Feb. 2000.
- [Sagayama99ASRU12]
Shigeki Sagayama, Shigeki Matsuda, Mitsuru Nakai and Hiroshi Shimodaira,
``Asynchronous-Transition HMM for Acoustic Modeling,''
Proc. IEEE Workshop on Automatic Speech Recognition and Understanding
(Keystone, Colorado), in Proceedings CD-ROM, Dec. 1999.
[postscript file available]
- [Sagayama99Robust05] (Invited Paper)
Shigeki Sagayama, ``Differential Approach to Model Adaptation,''
Proc. IEEE Workshop on Robust Methods for Speech Recognition in
Adverse Conditions (Robust99) (Tampere, Finland),
pp. 61--66, May 1999.
[postscript file available]
- [Matsunaga98ICASSP05]
Shoichi Matsunaga and Shigeki Sagayama, ``Two-Step Generation of
Variable-Word-Length Language Model Integrating Local and Global
Constraints,'' Proc. IEEE Int. Conf. of Acoust., Speech, and Signal
Processing (ICASSP98) (Seattle), May
1998.
- [Sagayama97ASRU12]
Shigeki Sagayama, Yoshikazu Yamaguchi, and Satoshi Takahashi,
``Jacobian Adaptation of Noisy Speech Models,'' Proc. IEEE Workshop on
Automatic Speech Recognition and Understanding (Santa Barbara),
pp. 396--403, Dec. 1997.
[postscript file available]
- [Matsunaga97Eurospeech09]
Shoichi Matsunaga and Shigeki Sagayama, ``Variable-Length Language
Modeling Integrating Global Constraints,'' Proc. Eurospeech 97
(Rhodes, Greece), pp. 2719--2722, Sep.
1997.
- [Yamaguchi97Eurospeech09]
Yoshikazu Yamaguchi, Satoshi Takahashi, and Shigeki Sagayama, ``Fast
Adaptation of Acoustic Models to Environmental Noise Using Jacobian
Adaptation Algorithm,'' Proc. Eurospeech 97 (Rhodes, Greece),
pp. 2051--2054, Sep. 1997.
- [Homma97ICASSP]
Shigeru Homma, Kiyoaki Aikawa, and Shigeki Sagayama,
``Improved Estimation of Supervision in Unsupervised Speaker
Adaptation,'' Proc. IEEE Int. Conf. of Acoust., Speech, and Signal
Processing (ICASSP97) (Munich), vol. 2, pp. 1023--1026, Apr.
1997.
- [TakahashiS97ICASSP]
Satoshi Takahashi and Shigeki Sagayama, ``Discrete Mixture HMM for
Speech Recognition,'' Proc. IEEE Int. Conf. of Acoust., Speech, and
Signal Processing (ICASSP97) (Munich), vol. 2, pp. 971--974, Apr.
1997.
- [Sagayama97ICASSP]
Shigeki Sagayama, Yoshikazu Yamaguchi, Satoshi Takahashi, and Jun-ichi
Takahashi, ``Jacobian Approach to Fast Acoustic Model Adaptation,''
Proc. IEEE Int. Conf. of Acoust., Speech, and Signal Processing
(ICASSP97) (Munich), vol. 2, pp. 835--838, Apr.
1997.
[postscript file available]
- [Sagayama97ESCA04] (Invited Paper)
Shigeki Sagayama and Kiyoaki Aikawa, ``Issues Relating to the Future
of ASR for Telecommunications Applications,'' Proc. ESCA/NATO Tutorial
and Research Workshop on Robust Speech Recognition for Unknown
Communication Channels, (Pont-a-Mousson, France, 17-18 April 1997),
pp. 75--81, Apr. 1997.
[postscript file available]
- [Yamada96ICSLP10]
Tomokazu Yamada and Shigeki Sagayama, ``LR-Parser-Driven Viterbi
Search With Hypotheses Merging Mechanism Using Context-Dependent Phone
Models,'' Proc. 1996 International Conference on Spoken Language
Processing (ICSLP96) (Philadelphia), pp. 2103--2106, Oct.
1996.
- [Homma96ICSLP10]
Shigeru Homma, Jun-ichi Takahashi, and Shigeki Sagayama, ``Iterative
Unsupervised Speaker Adaptation for Batch Dictation,'' Proc. 1996 Int.
Conf. on Spoken Language Processing (ICSLP96) (Philadelphia),
pp. 1141--1144, Oct. 1996.
- [Kitai96IVTTA10b]
Mikio Kitai, Tomokazu Yamada, Hajime Tsukada, Satoshi Takahashi,
Yoshiaki Noda, Jun-ichi Takahashi, Yuki Yoshida, Kazuhiro Arai,
Takashi Imoto, Kazuo Hakoda, Tomohisa Hirokawa, and Shigeki Sagayama,
``Experimental Interactive System for Telephone Applications with
Speech Recognition and Synthesis Functions,'' Proc. International
Workshop on Interactive Voice Technology for Telecommunications
Applications (IVTTA96),
Sep. 1996.
- [Kitai96IVTTA10a]
Mikio Kitai, Kazuo Hakoda, and Shigeki Sagayama, ``Trends of ASR and
TTS applications in Japan,'' Proc. of International Workshop on
Interactive Voice Technology for Telecommunications Applications
(IVTTA96), Sep. 1996.
- [TakahashiS96ICASSP]
Satoshi Takahashi and Shigeki Sagayama, ``Tied-Structure HMM Based on
Parameter Correlation for Efficient Model Training,'' Proc. IEEE
Int. Conf. of Acoust., Speech, and Signal Processing (ICASSP96)
(Atlanta), pp. I-467--470, 1996.
- [TakahashiJ96ICASSP]
Jun-ichi Takahashi and Shigeki Sagayama, ``Minimum Classification
Error Training for a Small Amount of Data Enhanced by
Vector-Field-Smoothed Bayesian Learning,'' Proc. IEEE Int. Conf. of
Acoust., Speech, and Signal Processing (ICASSP96) (Atlanta),
pp. II-597--600, 1996.
- [Arai95IWHIT10]
Kazuhiro Arai, Osamu Yoshioka, Yoshiaki Noda, Takashi Imoto, Tomokazu
Yamada, Satoshi Takahashi, Jun'ichi Takahashi, Noboru Sugamura, and
Shigeki Sagayama, ``Evaluation of a Multimodal System for Address Data
Entry Utilizing a Speech Recognition Server,'' Proc. of International
Workshop on Human Interface Technology, pp. 21--26, Oct.
1995.
- [Noda95Eurospeech09]
Yoshiaki Noda and Shigeki Sagayama, ``Fast and Accurate Beam Search
Using Forward Heuristic Functions in HMM-LR Speech Recognition,''
Proc. of Eurospeech95 (Madrid), WEam1A.5, pp. 913--916, Sep.
1995.
- [Jitsuhiro95Eurospeech09]
Takatoshi Jitsuhiro, Tomokazu Yamada, and Shigeki Sagayama, ``Syllabic
Duration Control for Vocabulary-Free Speech Recognition,''
Proc. Eurospeech95 (Madrid), pp. 15--18, Sep.
1995.
- [Arai95ESCA05]
Kazuhiro Arai, Osamu Yoshioka, Shigeki Sagayama and Noboru Sugamura,
``An Prototype of An Address Input System with Speech Recognition,''
Proc. ESCA Tutorial and Research Workshop on Spoken Dialog Systems,
pp. 213--216, June 1995.
- [Arai95HCI06]
Kazuhiro Arai, Osamu Yoshioka, Shigeki Sagayama and Noboru Sugamura,
``An Operation Analysis of An Address Input System with Speech
Recognition,'' Proc. Intenational Conference on Human Computer
Interaction '95, pp. 541--546, July 1995; also contained in a book:
{\sl Symbiosis of Human and Artifact,} Elsevier Science B. V.,
1995.
- [Sagayama95ICASSP05]
Shigeki Sagayama and Satoshi Takahashi, ``On the Use of Scalar
Quantization for Fast HMM Computation,'' Proc. Int. Conf. on
Acoustics, Speech and Signal Processing (ICASSP95) (Detroit),
pp. 213--216, May 1995.
[postscript file available]
- [TakahashiS95ICASSP05]
Satoshi Takahashi and Shigeki Sagayama, ``Four-level Tied Structure
for Efficient Representation of Acoustic Modeling,''
Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP95)
(Detroit), pp. 520--523, May
1995.
- [TakahashiJ95ICASSP05]
Jun-ichi Takahashi and Shigeki Sagayama, ``Vector-Field-Smoothed
Bayesian Learning for Incremental Speaker Adaptation,''
Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP95)
(Detroit), pp. 696--699, May
1995.
- [Takahashi94IVTTA09]
Jun-ichi Takahashi and Shigeki Sagayama, ``Fast Telephone Channel
Adaptation Based on Vector Field Smoothing Technique,''
Proc. International Workshop on Interactive Voice Technology for
Telecommunications Applications (IVTTA94) (Kyoto), pp. 97--100, May
1994.
- [Takahashi94ICSLP09]
Jun-ichi Takahashi and Shigeki Sagayama, ``Telephone Line
Characteristic Adaptation Using Vector Field Smoothing Technique,''
Proc. Int. Conf. on Acoustics, Speech and Signal Processing (ICSLP94)
(Yokohama), pp. 991--994, Sep.
1994.
- [Yamaguchi94ICSLP09]
Kouichi Yamaguchi, Harald Singer, Shoichi Matsunaga, and Shigeki
Sagayama, ``Speaker-Consistent Parsing for Speaker-Independent
Continuous Speech Recognition,'' Proc. Int. Conf. on Acoustics, Speech
and Signal Processing (ICSLP94), pp. 791--794, Sep.
1994.
- [Kosaka94ICSLP09]
Tetsuo Kosaka, Shoichi Matsunaga and Shigeki Sagayama,
``Tree-Structured Speaker Clustering for Speaker-Independent
Continuous Speech Recognition,'' Proc. Int. Conf. on Acoustics, Speech
and Signal Processing (ICSLP94), pp. 1375--1378, Sep.
1994.
- [Miyazawa94ICASSP03]
Yasunaga Miyazawa, Jun-ichi Takami, Shigeki Sagayama, and Shoichi
Matsunaga, ``All-phoneme Ergodic Hidden Markov Network for
Unsupervised Speaker Adaptation,'' Proc. Int. Conf. on Acoustics,
Speech and Signal Processing (ICASSP94), pp. I-249--252, Apr. 1994.
- [Kosaka94ICASSP03]
Tetsuo Kosaka and Shigeki Sagayama, ``Tree-Structured Speaker
Clustering for Fast Speaker Adaptation,'' Proc. Int. Conf. on
Acoustics, Speech and Signal Processing (ICASSP94), pp. I-245--248,
Apr. 1994.
- [Isotani93ASRworkshop]
Ryosuke Isotani, Shoichi Matsunaga, and Shigeki Sagayama, ``Continuous
Speech Recognitionn Using Stochatic Global Language Model,''
Proc. IEEE Workshop on Automatic Speech Recognition (Snowbird, USA),
1993.
- [Morimoto93Eurospeech]
Tsuyoshi Morimoto, Toshiyuki Takezawa, Fumihiro Yato, Shigeki
Sagayama, Toshihisa Tashiro, Masaaki Nagata, and Akira Kurematsu,
``ATR's Speech Translation System: ASURA,'' Proc. Eurospeech93
(Berlin), pp. 1291--1294,
Sep. 1993.
- [Sagayama93Eurospeech]
Shigeki Sagayama, Jun-ichi Takami, Akito Nagai, Harald Singer, Kouichi
Yamaguchi, Kazumi Ohkura, Kenji Kita, and Akira Kurematsu, ``ATREUS: a
Speech Recognition Front-end for a Speech Translation System,''
Proc. Eurospeech93 (Berlin), pp. 1287--1290, Sep.
1993.
- [Isotani93Eurospeech]
Ryosuke Isotani and Shigeki Sagayama, ``Speech Recognition Using
Particle $N$-grams and Content-Word $N$-grams,'' Proc. Eurospeech93
(Berlin), pp. 1955--1958, Sep.
1993.
- [Murakami93Eurospeech]
Jin'ichi Murakami, Hiroaki Yamamoto, and Shigeki Sagayama, `` On the
Automatic Acquisition of Stochastic Network Grammar using Ergodic
HMM,'' Proc. Eurospeech93 (Berlin), pp. 1327--1330,
Sep. 1993.
- [Kosaka93Eurospeech]
Tetsuo Kosaka, Edward Willems, Jun-Ichi Takami and Shigeki Sagayama,
``A Dynamic Approach to Speaker Adaptation of Hidden markov Networks
for Speech Recognition,'' Proc. Eurospeech93 (Berlin), pp. 363--366,
Sep. 1993.
- [Kikui93IJKAI]
Gen-ichiro Kikui, Mark Seligman, Toshiyuki Takezawa, Tsuyoshi
Morimoto, Masami Suzuki, Kenji Kita, Masaaki Nagata, Toshihisa
Tashiro, Heinrich Tropf, Shigeki Sagayama, Jun-ichi Takami, Kazumi
Ohkura and Akira Kurematsu, ``A Spoken Language Translation System:
ASURA,'' Proc. of International Joint Conference on Artificial
Intelligence (IJCAI93), 1993.
- [Nagai93ICASSP]
Akito Nagai, Koichi Yamaguchi, Shigeki Sagayama, and Akira Kurematsu,
``ATREUS: A Comparative Study of Continuous Speech Recognition Systems
at ATR,'' Proc. Int. Conf. on Acoustics, Speech and Signal Processing
(ICASSP93) (Minneapolis, USA), Vol. II, pp. 139--142, Apr.
1993.
- [Kosaka93ICASSP04]
Tetsuo Kosaka and Shigeki Sagayama, ``Rapid Speaker Adaptation Using
Speaker-Mixture Allophone Models Applied for Speaker Independent
Recognition,'' Proc. Int. Conf. on Acoustics, Speech and Signal
Processing (ICASSP93), Vol. II, pp. 570--573,
Apr. 1993.
- [Singer93ICASSP04]
Harald Singer and Shigeki Sagayama, ``Matrix Parser and its
Application to HMM-based Speech Recognition,'' Proc. Int. Conf. on
Acoustics, Speech and Signal Processing (ICASSP93) (Minneapolis), Vol.
II, pp. 295--298, Apr. 1993.
- [Takami92SST12]
Jun-ichi Takami, Akito Nagai, and Shigeki Sagayama, ``Speaker
Adaptation of the SSS (Successive State Splitting)-Based Hidden Markov
Network for Continuous Speech Recognition,'' Proc. SST92 (Fourth
Australian Int. Conf. on Speech Sci. and Tech.) (Brisbane),
pp. 437-442, Dec. 1992.
- [Kosaka92SST12]
Tetsuo Kosaka and Shigeki Sagayama, ``An Algorithm for Automatic HMM
Structure Generation in Speech Recognition,'' Proc. SST92 (Fourth
Australian Int. Conf. on Speech Sci. and Tech.) (Brisbane),
pp. 104--109, Dec. 1992.
- [Miyazawa92SST12]
Yasunaga Miyazawa and Shigeki Sagayama, ``Speaker-Normalized
HMM-Likelihood for Selecting a Reference Speaker in Speaker-Adaptive
Speech Recognition,'' Proc. SST92 (Fourth Australian Int. Conf. on
Speech Sci. and Tech.), pp. 431--436,
Dec. 1992.
- [Singer92SST12]
Harald Singer and Shigeki Sagayama, ``Suprasegmental Duration Control
with Matrix Parsing in Continuous Speech Recognition,'' Proc. SST92
(Fourth Australian Int. Conf. on Speech Sci. and Tech.) (Brisbane),
pp. 394--399, Dec. 1992.
- [Murakami92SST12]
Jin'ichi Murakami and Shigeki Sagayama, ``An Efficient Algorithm For
Using Word Trigram Models For Continuous Speech Recognition,''
Proc. SST92 (Fourth Australian Int. Conf. on Speech Sci. and Tech.)
(Brisbane), pp. 330-335
Dec. 1992.
- [Katagishi92SST12]
Kazuki Katagishi, Harald Singer, Kiyoaki Aikawa, Shigeki Sagayama,
``Linear Filtering of a Feature Vector Sequence for Speech
Recognition,'' Proc. SST92 (Fourth Australian Int. Conf. on Speech
Sci. and Tech.) (Brisbane), pp. 112--117,
Dec. 1992.
- [Sagayama92SST12]
Shigeki Sagayama, Masahide Sugiyama, Kazumi Ohkura, Jun-ichi Takami,
Akito Nagai, Harald Singer, Hiroaki Hattori, Keiichi Fukuzawa,
Yoshinaga Kato, Kouichi Yamaguchi, Jun'ichi Murakami, and Akira
Kurematsu, ``ATREUS: Continuous Speech Recognition Systems at ATR
Interpreting Telephony Research Laboratories,'' Proc. SST92 (Fourth
Australian Int. Conf. on Speech Sci. and Tech.) (Brisbane),
pp. 324--329 Dec. 1992.
- [Nagai92ICSLP10b]
Akito Nagai, Kenji Kita, Toshiyuki Hanazawa, Tadashi Suzuki, Tomohiro
Iwasaki, Tsuyoshi Kawabata, Kunio Nakajima, Kiyohiro Shikano, Tsuyoshi
Morimoto, Shigeki Sagayama, Akira Kurematsu, ``Hardware Implementation
of Realtime 1000-word HMM-LR Continuous Speech Recognition,''
Proc. Int. Conf. on Spoken Language Processing (Banff, Canada),
Vol. 1, pp. 237--240, Oct. 1992.
- [Nagai92ICSLP10a]
Akito Nagai, Junichi Takami, Shigeki Sagayama, ``The SSS-LR Continuous
Speech Recognition System: Integrating SSS-derived Allophone Models
and a Phoneme-Context-Dependent LR Parser,'' Proc. Int. Conf. on
Spoken Language Processing (Banff, Canada), Vol. 2, pp. 1511--1514,
Oct. 1992.
- [Kita92ICSLP10]
Kenji Kita, Tsuyoshi Morimoto, Kazumi Ohkura, Shigeki Sagayama,
``Continuously Spoken Sentence Recognition by HMM-LR,''
Proc. Int. Conf. on Spoken Language Processing (Banff, Canada),
pp. 305--308, Oct. 1992.
- [Yamaguchi92ICSLP10]
Kouichi Yamaguchi, Shigeki Sagayama, Kenji Kita, Frank K. Soong,
``Continuous Mixture HMM-LR Using the {\sl A}$^{*}$ Algorithm for
Continuous Speech Recognition,'' Proc. of 1992 Int. Conf. on Spoken
Language Processing (Banff, Canada), We.sAM.1.2, pp. 301--304,
Oct. 1992.
- [Ohkura92ICSLP10]
Kazumi Ohkura, Masahide Sugiyama and Shigeki Sagayama, ``Speaker
Adaptation Based on Transfer Vector Field Smoothing with Continuous
Mixture Density HMMs,'' Proc. of 1992 International Conference on
Spoken Language Processing (Banff, Canada), pp. 369--372,
Oct. 1992.
- [Rainton92ICSLP10]
David Rainton and Shigeki Sagayama, ``Optimal Error Criterion
Selection for HMM Minimum Misclassification Training,'' Proc. of
Int. Conf. on Spoken Language Processing (Banff, Canada), pp. 233--236
Oct. 1992.
- [Hattori92ICSLP10]
Hiroaki Hattori and Shigeki Sagayama, ``Vector Field Smoothing
Principle for Speaker Adaptation,'' Proc. Int. Conf. on Spoken
Language Processing (Banff, Canada), pp. 381--384,
Oct. 1992.
- [Morimoto92ICSLP10]
Tsuyoshi Morimoto, Toshiyuki Takezawa, Kazumi Ohkura, Masaaki Nagata,
Fumihiro Yato, Shigeki Sagayama, and Akira Kurematsu, ``Enhancement of
ATR's Spoken Language Translation System: SL-TRANS2,'' Proc. Int.
Conf. on Spoken Language Processing (Banff, Canada), pp. 397--400,
Oct. 1992.
- [Rainton92ISSPA07]
David Rainton, Shigeki Sagayama, ``A New Minimum Error Classification
Training Technique for HMM Based Speech Recognition,'' Proc. ISSPA
(Gold Coast, Australia), Aug.
1992.
- [Sagayama92SpeechTech]
Shigeki Sagayama, ``Speech Research at ATR Interpreting Telephony
Research Laboratories,'' Proc. Speech Technology (Tokyo), Vol. 5,
No. 4, Media Dimension Publishing Co., Ltd., Feb/Mar 1992.
- [Takami92ICASSP3]
Jun-ichi Takami and Shigeki Sagayama, ``A Successive State Splitting
Algorithm for Efficient Allophone Modeling,'' Proc. International
Conference on Acoustics, Speech and Signal Processing (ICASSP92) (San
Francisco), 66.6, Mar 1992.
- [Singer92ICASSP3]
Harald Singer, Shigeki Sagayama,``Pitch Dependent Phone Modelling for
HMM Based Speech Recognition,'' Proc. International Conference on
Acoustics, Speech and Signal Processing (ICASSP92) (San Francisco),
36.1, Mar 1992.
- [Takami91NNSPworkshop]
Jun-ichi Takami, Shigeki Sagayama, Atsuhiko Kai, ``Speech Recognition
by Combining Pairwise Discriminant Time-Delay Neural Networks and
Predictive LR-Parser,'' Proc. IEEE NNSP91 (Princeton), pp. 327-336,
Sep. 1991.
- [Nagai91Eurospeech]
Akito Nagai and Shigeki Sagayama, ``Phoneme-Context-Dependent LR
Parsing Algorithms for HMM-based Continuous Speech Recognition,''
Proc. Eurospeech91 (Genoa), 48.3, pp. 1397-1400,
1991.
- [Sagayama91Eurospeech]
Shigeki Sagayama, ``A Matrix Representation of HMM-based Speech
Recognition Algorithms,'' Proc. Eurospeech91 (Genoa), 42.5,
pp. 1225-1228, 1991.
- [Dantsuji91ICPhS]
Masatake Dantsuji and Shigeki Sagayama, ``A study on Distinctive
Features and Feature Hierarchies through Phoneme Environment
Clustering (PEC),'' Proc. Int. Conf. on Phonetical Sci. (ICPhS91)
(Aix-en-Provence), pp. 3:190-193,
1991.
- [Nakamura91ICASSP05]
Masami Nakamura, Shin-ichi Tamura, and Shigeki Sagayama, ``Phoneme
Recognition by Phoneme Filter Neural Networks,'' Proc. International
Conference on Acoustics, Speech and Signal Processing (ICASSP91)
(Toronto), 8.S2.12, pp. 85--88,
1991.
- [Takami91ICASSP05]
Jun-ichi Takami and Shigeki Sagayama, ``A Pairwise Discriminant
Approach to Robust Phoneme Recognition by Time-Delay Neural
Networks,'' Proc. International Conference on Acoustics, Speech and
Signal Processing (ICASSP91) (Toronto), 8.S2.13, pp. 89--92,
1991.
- [Sagayama91ICASSP05]
Shigeki Sagayama, Jun-ichi Takami, and Shigeru Homma, ``An Allophone
Clustering Technique Applied to Large Vocabulary Word Speech
Recognition,'' Proc. International Conference on Acoustics, Speech and
Signal Processing (ICASSP91) (Toronto), 56.S3.1, (not appeared in the
proceedings), 1991.
- [Hattori90ICSLP]
Hiroaki Hattori, Satoshi Nakamura, Kiyohiro Shikano, and Shigeki
Sagayama, ``Speaker Weighted Training of HMM Using Multiple Reference
Speakers,''
Proc. International Conference on Spoken Language Processing (ICSLP90)
(Kobe), 5.6, pp. 149-152,
Nov. 1990.
- [Takami90ICSLP]
Jun-ichi Takami and Shigeki Sagayama, ``Phoneme Recognition by Pairwise
Discriminant TDNN,'' Proc. International Conference on Spoken Language
Processing (Kobe), 16.5, pp. 677-680, 1990.
- [Abe90ICSLP]
Masanobu Abe and Shigeki Sagayama, ``Statistical Study on Voice
Individuality Conversion Across Different Languages,''
Proc. International Conference on Spoken Language Processing (ICSLP90)
(Kobe), 5.8, pp. 157-160, 1990.
- [Gurgen90ICSLP]
Fikret S. Gurgen, Shigeki Sagayama, and Sadaoki Furui, ``Line Spectrum
Pair Frequency-Based Distance Measures for Speech Recognition,'' Proc.
International Conference on Spoken Language Processing (ICSLP90)
(Kobe), 13.1, pp. 521-524, 1990.
- [Takahashi90ICSLP]
Satoshi Takahashi, Shoichi Matsunaga, and Shigeki Sagayama, ``Isolated
Word Recognition Using Pitch Pattern Information,''
Proc. International Conference on Spoken Language Processing (ICSLP90)
(Kobe), 13.9, pp. 553-556, 1990.
- [Matsunaga90ICSLP]
Shoichi Matsunaga and Shigeki Sagayama, ``Sentence Speech Recognition
Using Semantic Dependency Analysis,'' Proc. International Conference
on Spoken Language Processing (ICLSP90) (Kobe), 21.9, pp. 929-932,
1990.
- [Sagayama90ICSLP]
Shigeki Sagayama and Shigeru Homma, ``Estimation of Unknown Contexxt
Using a Phoneme Environment Clustering Algorithm,''
Proc. International Conference on Spoken Language Processing (ICSLP90)
(Kobe), 9.4, pp. 361-364, 1990.
- [Matsunaga90ICASSP]
Shoichi Matsunaga, Shigeki Sagayama, Shigeru Homma, and Sadaoki Furui,
``A Continuous Speech Recognition System Based on a Two-Level Grammar
Approach,'' Proc. International Conference on Acoustics, Speech and
Signal Processing (ICASSP90) (Albuquerque), S11.7, pp. 589-592,
1990.
- [Sagayama89ICASSP]
Shigeki Sagayama, ``Phoneme Environment Clustering for Speech
Recognition,'' Proc. International Conference on Acoustics, Speech and
Signal Processing (ICASSP89) (Glasgow), S8.3, pp. 397--400,
1989.
- [Sagayama86ICASSP]
Shigeki Sagayama and Fumitada Itakura, ``Duality Theory of Composite
Sinusoidal Modeling and Linear Prediction,'' Proc. International
Conference on Acoustics, Speech and Signal Processing (ICASSP86)
(Tokyo), 24.10, pp. 1261--1264,
1986.
- [Sagayama81VLSI]
Shigeki Sagayama and Fumitada Itakura, ``LSP Speech Synthesizer LSI
and Its Applications,'' Handout of First International Workshop on
VLSI for Communications Applications (Sanata Barbara), pp. 1--14,
1981.
- [Sagayama80IMAC]
Shigeki Sagayama and Fumitada Itakura, ``Speech Synthesis Using
Microprocessor by Composite Sinusoidal Modeling,'' Proc. IMAC'80,
pp. 307--317, 1980.
|