Stochastic vector mapping-based feature enhancement using prior model and environment adaptation for noisy speech recognition

Chia Hsin Hsieh, Chung Hsien Wu, Jun Yu Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents an approach to feature enhancement for noisy speech recognition. Three prior models are introduced to characterize clean speech, noise and noisy speech respectively using sequential noise estimation based on noise-normalized stochastic vector mapping. Environment adaptation is also adopted to reduce the mismatch between training data and test data. For AURORA2 database, the experimental results indicate that a 0.77% digit accuracy improvement for multi-condition training and 0.29% digit accuracy improvement for clean speech training were achieved without stereo training data compared to the SPLICE-based approach with recursive noise estimation. For MAT-BN Mandarin broadcast news database, a 2.6% syllable accuracy improvement for anchor speech and 4.2% syllable accuracy improvement for field report speech were obtained compared to the MCE-based approach.

Original languageEnglish
Title of host publicationINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
PublisherInternational Speech Communication Association
Pages29-32
Number of pages4
ISBN (Print)9781604234497
Publication statusPublished - 2006 Jan 1
EventINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA, United States
Duration: 2006 Sep 172006 Sep 21

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume1
ISSN (Electronic)1990-9772

Other

OtherINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
CountryUnited States
CityPittsburgh, PA
Period06-09-1706-09-21

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Stochastic vector mapping-based feature enhancement using prior model and environment adaptation for noisy speech recognition'. Together they form a unique fingerprint.

Cite this