| 2010 | Interspeech | Speaker adaptation based on system combination using speaker-class models. | Tetsuo Kosaka, Takashi Ito, Masaharu Katoh, Masaki Kohda |
| 2000 | Interspeech | Language modeling by stochastic dependency grammar for Japanese speech recognition. | Akinori Ito, Chiori Hori, Masaharu Katoh, Masaki Kohda |
| 1999 | Interspeech | A new metric for stochastic language model evaluation. | Akinori Ito, Masaki Kohda, Mari Ostendorf |
| 1997 | Interspeech | N-gram language model adaptation using small corpus for spoken dialog recognition. | Akinori Ito, Hideyuki Saitoh, Masaharu Katoh, Masaki Kohda |
| 1996 | Interspeech | Language modeling by string pattern n-gram for Japanese speech recognition. | Akinori Ito, Masaki Kohda |
| 1994 | Interspeech | A study on viterbi best-first search for isolated word recognition using duration-controlled HMM. | Masaharu Katoh, Masaki Kohda |
| 1990 | Interspeech | Lip-reading of Japanese vowels using neural networks. | Tomio Watanabe, Masaki Kohda |
| 1988 | COLING | Linguistic processing using a dependency structure grammar for speech recognition and understanding. | Shoichi Matsunaga, Masaki Kohda |
| 1987 | ICASSP | Word spotting method based on top-down phoneme verification. | Takeshi Kawabata, Masaki Kohda |
| 1986 | ICASSP | Word spotting method taking account of duration change characteristics for stable and transient parts of speech. | Takeshi Kawabata, Masaki Kohda |
| 1976 | ICASSP | Speech recognition in the question-answering system operated by conversational speech. | Masaki Kohda, Ryohei Nakatsu, Kiyohiro Shikano |
| 1976 | ICASSP | Spoken word recognition using the restricted number of learning samples. | Shuzo Saito, Masaki Kohda |