Toshiyuki Hanazawa

发表

HMM speech recognition using stochastic language models

Kenji Kita, Takeshi Kawabata, Toshiyuki Hanazawa, 1991 .

Advanced ASR Technologies for Mitsubishi Electric Speech Applications

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

Voice Activity Detection Using Density Ratio Esrimation of Speech and Noise

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2013 .

Phoneme recognition using time-delay neural networks

Geoffrey E. Hinton, Kiyohiro Shikano, Alexander H. Waibel, 1989, IEEE Trans. Acoust. Speech Signal Process..

Voice activity detection based on density ratio estimation and system combination

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

ATR HMM-LR continuous speech recognition system

Kenji Kita, Satoshi Nakamura, Kiyohiro Shikano, 1990, International Conference on Acoustics, Speech, and Signal Processing.

VQ-based speaker adaptation applied to HMM phoneme recognition

Satoshi Nakamura, Kiyohiro Shikano, Toshiyuki Hanazawa, 1989 .

Teacher-student Deep Clustering for Low-delay Single Channel Speech Separation

Jonathan Le Roux, Gordon Wichern, Toshiyuki Hanazawa, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction

Yuuki Tachioka, Toshiyuki Hanazawa, Tomohiro Iwasaki, 2013 .

Acoustic modeling for spontaneous speech recognition using syllable dependent models

Kunio Nakajima, Jun Ishii, Toshiyuki Hanazawa, 2000, INTERSPEECH.

Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models

Alex Waibel, Geoffrey E. Hinton, Kiyohiro Shikano, 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

On the robustness of HMM and ANN speech recognition algorithms

Shigeru Katagiri, Kiyohiro Shikano, Erik McDermott, 1990, ICSLP.

Multichannel NMF with Reduced Computational Complexity for Speech Recognition

Shingo Uenohara, Takanobu Uramoto, Ken'ichi Furuya, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Reducing Computational Complexity of Multichannel Nonnegative Matrix Factorization Using Initial Value Setting for Speech Recognition

Shingo Uenohara, Takanobu Uramoto, Ken'ichi Furuya, 2018, CISIS.

HMM continuous speech recognition using stochastic language models

Kenji Kita, Takeshi Kawabata, Toshiyuki Hanazawa, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Phrase spotting using pitch pattern information

Kunio Nakajima, Yoshiharu Abe, Toshiyuki Hanazawa, 1995, EUROSPEECH.

Hardware implementation of realtime 1000-word HMM-LR continuous speech recognition

Kenji Kita, Kiyohiro Shikano, Akira Kurematsu, 1992, ICSLP.

Dictation Machine Based on Japanese Character Source Modeling

Kiyohiro Shikano, Sadaoki Furui, Takeshi Kawabata, 1994, Int. J. Pattern Recognit. Artif. Intell..

Japanese phonetic typewriter using HMM phone units and syllable trigrams

Kiyohiro Shikano, Takeshi Kawabata, Katsunobu Itou, 1990, ICSLP.

Teacher-Student Deep Clustering For Low-Delay Channel Speech Separation

Jonathan Le Roux, Gordon Wichern, Toshiyuki Hanazawa, 2020 .

Duration control methods for HMM phoneme recognition

Kiyohiro Shikano, Takeshi Kawabata, Toshiyuki Hanazawa, 1988 .

Japanese Phonetic Typewriter Using HMM Phone Recognition and Stochastic Phone-Sequence Modeling

Kiyohiro Shikano, Takeshi Kawabata, Toshiyuki Hanazawa, 1991 .