The Use of Overlapped Sub-Bands in Multi-Band, Multi-SNR, Multi-Path Recognition of Noisy Word Utterances

スポンサーリンク

概要

• 論文の詳細を見る

• A solution to the problem of improving robustness to noise in automatic speech recognition is presented in the framework of multi-band, multi-SNR, and multi-path approaches. In our word recognizer, the whole frequency band is divided into seven-overlapped subbands, and then sub-band noisy phoneme HMMs are trained on speech data mixed with the filtered white Gaussian noise at multiple SNRs. The acoustic model of a word is built as a set of concatenations of clean and noisy sub-band phoneme HMMs arranged in parallel. A Viterbi decoder allows a search path to transit to another SNR condition at a phoneme boundary. The recognition scores of the sub-bands are then recombined to give the score for a word. Experiments show that the overlapped seven-band system yields the best performance under nonstationary ambient noises. It is also shown that the use of filtered white Gaussian noise is advantageous for training noisy phoneme HMMs.

• （社）電子情報通信学会の論文
• 2008-06-01

著者

• Takagi Kazuyuki

  University Of Electro-communications

• OZEKI Kazuhiko

  University of Electro-Communications

• TSUBOI Yutaka

  University of Electro-Communications

• IHARA Takehiro

  University of Electro-Communications

関連論文

• Effectiveness of Word String Language Models on Noisy Broadcast News Speech Recognition
• The Use of Overlapped Sub-Bands in Multi-Band, Multi-SNR, Multi-Path Recognition of Noisy Word Utterances
• Automatic Adjustment of Subband Likelihood Recombination Weights for Improving Noise-Robustness of a Multi-SNR Multi-Band Speaker Identification System(Speech and Hearing)

スポンサーリンク