Towards ASR on partially corrupted speech

Hynek Hermansky, Sangita Tibrewala, Misha Pavel

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

107 Citations (Scopus)

Abstract

A new highly parallel approach to automatic recognition of speech, inspired by early Fletcher's research on Articulation Index, and based on independent probability estimates in several sub-bands of the available speech spectrum, is presented. The approach is especially suitable for situations when part of the spectrum of speech is corrupted. In such cases, it can yield an order-of-magnitude improvement in the error rate over a conventional full-band recognizer.

Original languageEnglish (US)
Title of host publicationInternational Conference on Spoken Language Processing, ICSLP, Proceedings
Editors Anon
PublisherIEEE
Pages462-465
Number of pages4
Volume1
StatePublished - 1996
EventProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4) - Philadelphia, PA, USA
Duration: Oct 3 1996Oct 6 1996

Other

OtherProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4)
CityPhiladelphia, PA, USA
Period10/3/9610/6/96

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Hermansky, H., Tibrewala, S., & Pavel, M. (1996). Towards ASR on partially corrupted speech. In Anon (Ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings (Vol. 1, pp. 462-465). IEEE.

Towards ASR on partially corrupted speech. / Hermansky, Hynek; Tibrewala, Sangita; Pavel, Misha.

International Conference on Spoken Language Processing, ICSLP, Proceedings. ed. / Anon. Vol. 1 IEEE, 1996. p. 462-465.

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

Hermansky, H, Tibrewala, S & Pavel, M 1996, Towards ASR on partially corrupted speech. in Anon (ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings. vol. 1, IEEE, pp. 462-465, Proceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4), Philadelphia, PA, USA, 10/3/96.
Hermansky H, Tibrewala S, Pavel M. Towards ASR on partially corrupted speech. In Anon, editor, International Conference on Spoken Language Processing, ICSLP, Proceedings. Vol. 1. IEEE. 1996. p. 462-465
Hermansky, Hynek ; Tibrewala, Sangita ; Pavel, Misha. / Towards ASR on partially corrupted speech. International Conference on Spoken Language Processing, ICSLP, Proceedings. editor / Anon. Vol. 1 IEEE, 1996. pp. 462-465
@inproceedings{508f2df89c7e485ebcaca88123db9399,
title = "Towards ASR on partially corrupted speech",
abstract = "A new highly parallel approach to automatic recognition of speech, inspired by early Fletcher's research on Articulation Index, and based on independent probability estimates in several sub-bands of the available speech spectrum, is presented. The approach is especially suitable for situations when part of the spectrum of speech is corrupted. In such cases, it can yield an order-of-magnitude improvement in the error rate over a conventional full-band recognizer.",
author = "Hynek Hermansky and Sangita Tibrewala and Misha Pavel",
year = "1996",
language = "English (US)",
volume = "1",
pages = "462--465",
editor = "Anon",
booktitle = "International Conference on Spoken Language Processing, ICSLP, Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Towards ASR on partially corrupted speech

AU - Hermansky, Hynek

AU - Tibrewala, Sangita

AU - Pavel, Misha

PY - 1996

Y1 - 1996

N2 - A new highly parallel approach to automatic recognition of speech, inspired by early Fletcher's research on Articulation Index, and based on independent probability estimates in several sub-bands of the available speech spectrum, is presented. The approach is especially suitable for situations when part of the spectrum of speech is corrupted. In such cases, it can yield an order-of-magnitude improvement in the error rate over a conventional full-band recognizer.

AB - A new highly parallel approach to automatic recognition of speech, inspired by early Fletcher's research on Articulation Index, and based on independent probability estimates in several sub-bands of the available speech spectrum, is presented. The approach is especially suitable for situations when part of the spectrum of speech is corrupted. In such cases, it can yield an order-of-magnitude improvement in the error rate over a conventional full-band recognizer.

UR - http://www.scopus.com/inward/record.url?scp=0030365517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030365517&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 462

EP - 465

BT - International Conference on Spoken Language Processing, ICSLP, Proceedings

A2 - Anon, null

PB - IEEE

ER -