Analog auditory perception model for robust speech recognition

Yunbin Deng, Shantanu Chakrabartty, Gert Cauwenberghs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

An auditory perception model for noise-robust speech feature extraction is presented. The model assumes continuous-time filtering and rectification, amenable to real-time, low-power analog VLSI implementation. A 3mm × 3mm CMOS chip in 0.5μm CMOS technology implements the general form of the model with digitally programmable filter parameters. Experiments on the TI-DIGIT database demonstrate consistent robustness of the new features to noise of various statistics, yielding significant improvements in digit recognition accuracy over models identically trained using Mel-scale frequency cepstral coefficient (MFCC) features.

Original languageEnglish
Title of host publication2004 IEEE International Joint Conference on Neural Networks - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1705-1709
Number of pages5
ISBN (Print)0780383591
DOIs
StatePublished - 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary
Duration: Jul 25 2004Jul 29 2004

Publication series

NameIEEE International Conference on Neural Networks - Conference Proceedings
Volume3
ISSN (Print)1098-7576

Conference

Conference2004 IEEE International Joint Conference on Neural Networks - Proceedings
Country/TerritoryHungary
CityBudapest
Period07/25/0407/29/04

Fingerprint

Dive into the research topics of 'Analog auditory perception model for robust speech recognition'. Together they form a unique fingerprint.

Cite this