Noise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we propose a new noise suppression method, that is best used as a preprocessor for time-lag speech recognition. Assuming that a time lag of a few seconds is acceptable in various speech recognition applications, the proposed method is realized as a combination of forward and backward estimation flows over time. Each estimation flow is based on the optimally modified log spectral amplitude (OM-LSA) speech estimator, but a look-ahead estimation mechanism is additionally equipped to make the estimation more robust. Evaluation experiments using various databases confirm that the speech recognition accuracy can be greatly improved by adding the proposed method to the existing system.

• 一般社団法人 日本音響学会の論文

著者

• Obuchi Yasunari

  Central Research Laboratory Hitachi Ltd.

• Togami Masahito

  Central Research Laboratory Hitachi Ltd.

• Takeda Ryu

  Central Research Laboratory, Hitachi Ltd.

関連論文

• Multi-Input Feature Combination in the Cepstral Domain for Practical Speech Recognition Systems
• Intentional Voice Command Detection for Trigger-Free Speech Interface
• Emotion Recognition using Mel-Frequency Cepstral Coefficients
• Stepwise Phase Difference Restoration Method for DOA Estimation of Multiple Sources
• Multichannel Two-Stage Beamforming with Unconstrained Beamformer and Distortion Reduction
• Noise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation
• Emotion Recognition using Mel-Frequency Cepstral Coefficients

スポンサーリンク