Takahiro Oku

According to our database, Takahiro Oku authored at least 13 papers between 2008 and 2015.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2015

Discriminative bilinear language modeling for broadcast transcriptions.

Akio Kobayashi, Manon Ichiki, Takahiro Oku, Kazuo Onoe, Shoei Sato

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

2013

Lightly supervised training for risk-based discriminative language models.

Akio Kobayashi, Takahiro Oku, Yuya Fujita, Shoei Sato

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Progressive language model adaptation for disaster broadcasting with closed-captions.

Takahiro Oku, Yuya Fujita, Akio Kobayashi, Shoei Sato

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2013

2012

Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription.

Akio Kobayashi, Takahiro Oku, Toru Imai, Seiichi Nakagawa

IEICE Trans. Inf. Syst., 2012

Low-latency speaker diarization based on Bayesian information criterion with multiple phoneme classes.

Takahiro Oku, Shoei Sato, Akio Kobayashi, Shinichi Homma, Toru Imai

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Multi-objective optimization for semi-supervised discriminative language modeling.

Akio Kobayashi, Takahiro Oku, Toru Imai, Seiichi Nakagawa

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Speaker adaptation intensively weighted on mis-recognized speech segments.

Takahiro Oku, Yuya Fujita, Akio Kobayashi, Toru Imai

Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2012

2011

Lattice-Based Risk Minimization Training for Unsupervised Language Model Adaptation.

Akio Kobayashi, Takahiro Oku, Shinichi Homma, Toru Imai, Seiichi Nakagawa

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

2010

Learning Speech Variability in Discriminative Acoustic Model Adaptation.

Shoei Sato, Takahiro Oku, Shinichi Homma, Akio Kobayashi, Toru Imai

IEICE Trans. Inf. Syst., 2010

Speech recognition with a seamlessly updated language model for real-time closed-captioning.

Toru Imai, Shinichi Homma, Akio Kobayashi, Takahiro Oku, Shoei Sato

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Learning task-dependent speech variability in discriminative acoustic model adaptation.

Shoei Sato, Takahiro Oku, Shinichi Homma, Akio Kobayashi, Toru Imai

Proceedings of the IEEE International Conference on Acoustics, 2010

2008

Discriminative rescoring based on minimization of word errors for transcribing broadcast news.

Akio Kobayashi, Takahiro Oku, Shinichi Homma, Shoei Sato, Toru Imai, Tohru Takagi

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

New Real-Time Closed-Captioning System for Japanese Broadcast News Programs.

Shinichi Homma, Akio Kobayashi, Takahiro Oku, Shoei Sato, Toru Imai, Tohru Takagi

Proceedings of the Computers Helping People with Special Needs, 2008