Noise processing DTW algorithms for speech recognition systems

Alberto D. Berstein, Ilan D. Shallom

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

2 Scopus citations

Abstract

The problem of Speech Recognition in a noisy environment is addressed. Particularly the mismatch problem originated when training a system in a "clean" environment and operating it in a noisy one. When measuring the similarity between a noisy test utterance and a list of clean templates a correction process, based on a series of Wiener filters built using the hypothesized clean template, is applied to the feature vectors of the noisy word. The filtering process is optimized as a by product of the Dynamic Programing algorithm of the scoring step. Tests were conducted at the simulation level on two data bases, one in Hebrew and the second in Japanese, using additive white noise and real world car noise at different SNRs. The method shows a very good performance and compares well with other methods proposed in the literature.

Original languageEnglish
Title of host publicationProceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
PublisherInstitute of Electrical and Electronics Engineers
Pages293-296
Number of pages4
ISBN (Electronic)0879426780, 9780879426781
DOIs
StatePublished - 1 Jan 1991
Externally publishedYes
Event17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991 - Tel Aviv, Israel
Duration: 5 Mar 19917 Mar 1991

Publication series

NameProceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

Conference

Conference17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
Country/TerritoryIsrael
CityTel Aviv
Period5/03/917/03/91

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Noise processing DTW algorithms for speech recognition systems'. Together they form a unique fingerprint.

Cite this