Chipset for speech recognition in noisy environment

Zeev M. Rannon, Eli Shabiro, Ilan D. Shallom

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

Abstract

A high performance, noise robust, low cost chipset for automatic speech recognition is presented. It can be incorporated in a large range of consumer products where hands free operation in noisy environment is essential. The chipset recognizes isolated words in speaker-dependent mode. It implements a noise immune, DTW algorithm, achieving a recognition rate of 97%, when tested with a 16 words vocabulary of noisy speech at 3dB SNR and when tested in a moving car. This result is obtained using only two user trained templates per word. For enabling user-friendly man-machine interface, speech compression and synthesis for vocal prompting are also performed by the chipset.

Original languageEnglish
Title of host publicationDigest of Technical Papers - IEEE International Conference on Consumer Electronics
PublisherInstitute of Electrical and Electronics Engineers
Pages268-269
Number of pages2
ISBN (Print)0780308433
StatePublished - 1 Jan 1993
Externally publishedYes
EventProceedings of the IEEE 1993 International Conference on Consumer Electronics - Rosemont, IL,USA
Duration: 8 Jun 199310 Jun 1993

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)0747-668X

Conference

ConferenceProceedings of the IEEE 1993 International Conference on Consumer Electronics
CityRosemont, IL,USA
Period8/06/9310/06/93

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Chipset for speech recognition in noisy environment'. Together they form a unique fingerprint.

Cite this