Speech Enhancement by Profile Fitting Method (<Special Issue>Special Issue on Speech Information Processing)

スポンサーリンク

概要

• 論文の詳細を見る

• It is believed that distant-talking speech recognition in a noisy environment requires a large-scale microphone array. However, this cannot fit into small consumer devices. Our objective is to improve the performance with a limited number of microphones (preferably only left and right). Tn this paper, we focused on a profile that is the shape of the power distribution according to the beamforming direction. An observed profile can be decomposed into known profiles for directional sound sources and a non-directional background sound source. Evaluations confirmed this method reduced the CER (Character Error Ratio) for the dictation task by more than 20% compared to a conventional 2-channel Adaptive Spectral Subtraction beamformer in a non-reverberant environment.

• 社団法人電子情報通信学会の論文
• 2003-03-01

著者

• Ichikawa Osamu

  Tokyo Research Laboratory Ibm Japan Ltd.

• Takiguchi Tetsuya

  Ibm Tokyo Research Laboratory

• Ichikawa O

  Tokyo Research Laboratory Ibm Japan Ltd.

• Nishimura Masafumi

  Ibm Tokyo Research Laboratory

• Nishimura Masafumi

  Tokyo Research Lab. Ibm Japan

• TAKIGUCHI Tetsuya

  Tokyo Research Laboratory, IBM Japan Ltd.

関連論文

• Automatic Prosody Labeling Using Multiple Models for Japanese(Speech and Hearing)
• Local Peak Enhancement for In-Car Speech Recognition in Noisy Environment
• Simultaneous Adaptation of Echo Cancellation and Spectral Subtraction for In-Car Speech Recognition(Speech Enhancement, Multi-channel Acoustic Signal Processing)
• Sound Source Localization Using a Profile Fitting Method with Sound Reflectors(Speech Dynamics by Ear, Eye, Mouth and Machine)
• Speech Enhancement by Profile Fitting Method (Special Issue on Speech Information Processing)
• Improved HMM Separation for Distant-Talking Speech Recognition(Speech Dynamics by Ear, Eye, Mouth and Machine)

スポンサーリンク