Toru Imai

Akio Kobayashi, Takahiro Oku, Toru Imai, Seiichi Nakagawa: Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription. IEICE Transactions 95-D(11): 2674-2681 (2012)

Takahiro Oku, Shoei Sato, Akio Kobayashi, Shinichi Homma, Toru Imai: Low-latency speaker diarization based on Bayesian information criterion with multiple phoneme classes. ICASSP 2012: 4189-4192

Akio Kobayashi, Takahiro Oku, Toru Imai, Seiichi Nakagawa: Multi-objective optimization for semi-supervised discriminative language modeling. ICASSP 2012: 4997-5000

Akio Kobayashi, Takahiro Oku, Shinichi Homma, Toru Imai, Seiichi Nakagawa: Lattice-Based Risk Minimization Training for Unsupervised Language Model Adaptation. INTERSPEECH 2011: 1453-1456

Shoei Sato, Takahiro Oku, Shinichi Homma, Akio Kobayashi, Toru Imai: Learning Speech Variability in Discriminative Acoustic Model Adaptation. IEICE Transactions 93-D(9): 2370-2378 (2010)

Shoei Sato, Takahiro Oku, Shinichi Homma, Akio Kobayashi, Toru Imai: Learning task-dependent speech variability in discriminative acoustic model adaptation. ICASSP 2010: 4910-4913

Toru Imai, Shinichi Homma, Akio Kobayashi, Takahiro Oku, Shoei Sato: Speech recognition with a seamlessly updated language model for real-time closed-captioning. INTERSPEECH 2010: 262-265

Kazuo Onoe, Shoei Sato, Shinichi Homma, Akio Kobayashi, Toru Imai, Tohru Takagi: Bi-Spectral Acoustic Features for Robust Speech Recognition. IEICE Transactions 91-D(3): 631-634 (2008)

Shoei Sato, Akio Kobayashi, Kazuo Onoe, Shinichi Homma, Toru Imai, Tohru Takagi, Tetsunori Kobayashi: Mutual Information Based Dynamic Integration of Multiple Feature Streams for Robust Real-Time LVCSR. IEICE Transactions 91-D(3): 815-824 (2008)

Shinichi Homma, Akio Kobayashi, Takahiro Oku, Shoei Sato, Toru Imai, Tohru Takagi: New Real-Time Closed-Captioning System for Japanese Broadcast News Programs. ICCHP 2008: 651-654

Akio Kobayashi, Takahiro Oku, Shinichi Homma, Shoei Sato, Toru Imai, Tohru Takagi: Discriminative rescoring based on minimization of word errors for transcribing broadcast news. INTERSPEECH 2008: 1574-1577

Akio Kobayashi, Kazuo Onoe, Shinichi Homma, Shoei Sato, Toru Imai: Word Error Rate Minimization Using an Integrated Confidence Measure. IEICE Transactions 90-D(5): 835-843 (2007)

Toru Imai, Shoei Sato, Shinichi Homma, Kazuo Onoe, Akio Kobayashi: Online Speech Detection and Dual-Gender Speech Recognition for Captioning Broadcast News. IEICE Transactions 90-D(8): 1286-1291 (2007)

Shoei Sato, Kazuo Onoe, Akio Kobayashi, Shinichi Homma, Toru Imai, Tohru Takagi, Tetsunori Kobayashi: Dynamic integration of multiple feature streams for robust real-time LVCSR. INTERSPEECH 2007: 1146-1149

Shoei Sato, Kazuo Onoe, Akio Kobayashi, Toru Imai: Robust Speech Recognition by Using Compensated Acoustic Scores. IEICE Transactions 89-D(3): 915-921 (2006)

Toru Imai, Shoei Sato, Akio Kobayashi, Kazuo Onoe, Shinichi Homma: Online speech detection and dual-gender speech recognition for captioning broadcast news. INTERSPEECH 2006

Akio Kobayashi, Kazuo Onoe, Shoei Sato, Toru Imai: Word error rate minimization using an integrated confidence measure. INTERSPEECH 2005: 1453-1456

Toru Imai, Hideki Tanaka, Akio Ando, Haruo Isono: Progressive early decision of speech recognition results by comparing most likely word sequences. Systems and Computers in Japan 34(14): 73-82 (2003)

Toru Imai, Atsushi Matsui, Shinichi Homma, Takeshi Kobayakawa, Kazuo Onoe, Shoei Sato, Akio Ando: Speech recognition with a re-speak method for subtitling live broadcasts. INTERSPEECH 2002

Kazuo Onoe, Hiroyuki Segi, Takeshi Kobayakawa, Shoei Sato, Toru Imai, Akio Ando: Filter bank subtraction for robust speech recognition. INTERSPEECH 2002

Atsushi Matsui, Hiroyuki Segi, Akio Kobayashi, Toru Imai, Akio Ando: Speech recognition of broadcast sports news. INTERSPEECH 2001: 709-712

Shinichi Homma, Akio Kobayashi, Shoei Sato, Toru Imai, Akio Ando: Speech recognition of Japanese news commentary. INTERSPEECH 2001: 859-862

Shoei Sato, Toru Imai, Hideki Tanaka, Akio Ando: Selective training of HMMs by using two-stage clustering. INTERSPEECH 2000: 726-729

Akio Ando, Akio Kobayashi, Toru Imai: A thesaurus-based statistical language model for broadcast news transcription. ICSLP 1998

Akio Kobayashi, Kazuo Onoe, Toru Imai, Akio Ando: Time dependent language model for broadcast news transcription and its post-correction. ICSLP 1998

Richard M. Schwartz, Toru Imai, Francis Kubala, Long Nguyen, John Makhoul: A maximum likelihood model for topic classification of broadcast news. EUROSPEECH 1997

Rajiv Trehan, Nobuyuki Sawashima, Akira Morishita, Ichiro Tomoda, Toru Imai, Ken-ichi Maeda: Concurrent Object Oriented 'C' (cooC). SIGPLAN Notices 28(2): 45-52 (1993)

Toru Imai: Detecting More Independent Loops across Hierarchical Structures. ICCI 1992: 168-172