The search functionality is under construction.
The search functionality is under construction.

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

Yutaka TSUBOI, Takehiro IHARA, Kazuyuki TAKAGI, Kazuhiko OZEKI

  • Full Text Views

    0

  • Cite this

Summary :

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 sub-bands, 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.

Publication
IEICE TRANSACTIONS on Information Vol.E91-D No.6 pp.1774-1782
Publication Date
2008/06/01
Publicized
Online ISSN
1745-1361
DOI
10.1093/ietisy/e91-d.6.1774
Type of Manuscript
PAPER
Category
Speech and Hearing

Authors

Keyword