Masaharu Katoh

12 papers A 3C 1Journal 6Unranked 2
YearRankTypeTitle / Venue / Authors
2010 A conf
Lecture speech recognition by combining word graphs of various acoustic models.
INTERSPEECH
Tetsuo Kosaka, Keisuke Goto, Takashi Ito, Masaharu Katoh
2010 A conf
Speaker adaptation based on system combination using speaker-class models.
INTERSPEECH
Tetsuo Kosaka, Takashi Ito, Masaharu Katoh, Masaki Kohda
2010 J jnl
Unsupervised Speaker Adaptation Using Speaker-Class Models for Lecture Speech Recognition.
IEICE Trans. Inf. Syst.
Tetsuo Kosaka, Yuui Takeda, Takashi Ito, Masaharu Katoh, Masaki Kohda
2009 J jnl
Dictation of Japanese Speech Based on Kana and Kanji Character String.
Int. J. Comput. Process. Orient. Lang.
Akinori Ito, Hiroaki Kinno, Masaharu Katoh, Tetsuo Kosaka, Masaki Kohda
2009 C conf
Improvement of Speaker Vector-Based Speaker Verification.
IAS
Naoki Tadokoro, Tetsuo Kosaka, Masaharu Katoh, Masaki Kohda
2005 J jnl
Robust Speech Recognition Using Discrete-Mixture HMMs.
IEICE Trans. Inf. Syst.
Tetsuo Kosaka, Masaharu Katoh, Masaki Kohda
2002 J jnl
Construction and evaluation of language models based on stochastic context-free grammar for speech recognition Chiori Hori, Masaharu Katoh, Akinori Ito, Masaki Koh.
Syst. Comput. Jpn.
Chiori Hori, Masaharu Katoh, Akinori Ito, Masaki Kohda
2002 J jnl
Erratum: Language modeling by stochastic dependency grammer for Japanese speech recognition.
Syst. Comput. Jpn.
Akinori Ito, Chiori Hori, Masaharu Katoh, Masaki Kohda
2001 J jnl
Language modeling by stochastic dependency grammar for Japanese speech recognition.
Syst. Comput. Jpn.
Akinori Ito, Chiori Hori, Masaharu Katoh, Masaki Kohda
2000 A conf
Language modeling by stochastic dependency grammar for Japanese speech recognition.
INTERSPEECH
Akinori Ito, Chiori Hori, Masaharu Katoh, Masaki Kohda
1997 — conf
N-gram language model adaptation using small corpus for spoken dialog recognition.
EUROSPEECH
Akinori Ito, Hideyuki Saitoh, Masaharu Katoh, Masaki Kohda
1994 — conf
A study on viterbi best-first search for isolated word recognition using duration-controlled HMM.
ICSLP
Masaharu Katoh, Masaki Kohda