Building an ASR system for Noisy environments: SRI's 2001 SPINE evaluation system

Venkata Ramana Rao Gadde, Andreas Stolcke, Dimitra Vergyri, Jing Zheng, Mustafa (Kemal) Sonmez, Anand Venkataraman

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

9 Citations (Scopus)

Abstract

We describe SRI's recognition system as used in the 2001 DARPA Speech in Noisy Environments (SPINE) evaluation. The SPINE task involves recognition of speech in simulated military environments. The task had some unique challenges, including segmentation of foreground speech from noisy background, the need for robust acoustic models to handle noisy speech, and development of language models from limited training data. In developing the SRI evaluation system for this task, we addressed each of these challenges using a combination of state-of-the-art techniques, including several types of feature normalization, model adaptation, class-based language modeling, multi-pass segmentation and recognition, and word posterior-based decoding and system combination.

Original languageEnglish (US)
Title of host publication7th International Conference on Spoken Language Processing, ICSLP 2002
PublisherInternational Speech Communication Association
Pages1577-1580
Number of pages4
StatePublished - 2002
Externally publishedYes
Event7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, United States
Duration: Sep 16 2002Sep 20 2002

Other

Other7th International Conference on Spoken Language Processing, ICSLP 2002
CountryUnited States
CityDenver
Period9/16/029/20/02

Fingerprint

evaluation
normalization
language
acoustics
Military
Evaluation
segmentation
Segmentation
Decoding
Normalization
Language Modeling
Acoustics
Language Model

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Gadde, V. R. R., Stolcke, A., Vergyri, D., Zheng, J., Sonmez, M. K., & Venkataraman, A. (2002). Building an ASR system for Noisy environments: SRI's 2001 SPINE evaluation system. In 7th International Conference on Spoken Language Processing, ICSLP 2002 (pp. 1577-1580). International Speech Communication Association.

Building an ASR system for Noisy environments : SRI's 2001 SPINE evaluation system. / Gadde, Venkata Ramana Rao; Stolcke, Andreas; Vergyri, Dimitra; Zheng, Jing; Sonmez, Mustafa (Kemal); Venkataraman, Anand.

7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association, 2002. p. 1577-1580.

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

Gadde, VRR, Stolcke, A, Vergyri, D, Zheng, J, Sonmez, MK & Venkataraman, A 2002, Building an ASR system for Noisy environments: SRI's 2001 SPINE evaluation system. in 7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association, pp. 1577-1580, 7th International Conference on Spoken Language Processing, ICSLP 2002, Denver, United States, 9/16/02.
Gadde VRR, Stolcke A, Vergyri D, Zheng J, Sonmez MK, Venkataraman A. Building an ASR system for Noisy environments: SRI's 2001 SPINE evaluation system. In 7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association. 2002. p. 1577-1580
Gadde, Venkata Ramana Rao ; Stolcke, Andreas ; Vergyri, Dimitra ; Zheng, Jing ; Sonmez, Mustafa (Kemal) ; Venkataraman, Anand. / Building an ASR system for Noisy environments : SRI's 2001 SPINE evaluation system. 7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association, 2002. pp. 1577-1580
@inproceedings{014bdf5fba00446896d72d22bb979b21,
title = "Building an ASR system for Noisy environments: SRI's 2001 SPINE evaluation system",
abstract = "We describe SRI's recognition system as used in the 2001 DARPA Speech in Noisy Environments (SPINE) evaluation. The SPINE task involves recognition of speech in simulated military environments. The task had some unique challenges, including segmentation of foreground speech from noisy background, the need for robust acoustic models to handle noisy speech, and development of language models from limited training data. In developing the SRI evaluation system for this task, we addressed each of these challenges using a combination of state-of-the-art techniques, including several types of feature normalization, model adaptation, class-based language modeling, multi-pass segmentation and recognition, and word posterior-based decoding and system combination.",
author = "Gadde, {Venkata Ramana Rao} and Andreas Stolcke and Dimitra Vergyri and Jing Zheng and Sonmez, {Mustafa (Kemal)} and Anand Venkataraman",
year = "2002",
language = "English (US)",
pages = "1577--1580",
booktitle = "7th International Conference on Spoken Language Processing, ICSLP 2002",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Building an ASR system for Noisy environments

T2 - SRI's 2001 SPINE evaluation system

AU - Gadde, Venkata Ramana Rao

AU - Stolcke, Andreas

AU - Vergyri, Dimitra

AU - Zheng, Jing

AU - Sonmez, Mustafa (Kemal)

AU - Venkataraman, Anand

PY - 2002

Y1 - 2002

N2 - We describe SRI's recognition system as used in the 2001 DARPA Speech in Noisy Environments (SPINE) evaluation. The SPINE task involves recognition of speech in simulated military environments. The task had some unique challenges, including segmentation of foreground speech from noisy background, the need for robust acoustic models to handle noisy speech, and development of language models from limited training data. In developing the SRI evaluation system for this task, we addressed each of these challenges using a combination of state-of-the-art techniques, including several types of feature normalization, model adaptation, class-based language modeling, multi-pass segmentation and recognition, and word posterior-based decoding and system combination.

AB - We describe SRI's recognition system as used in the 2001 DARPA Speech in Noisy Environments (SPINE) evaluation. The SPINE task involves recognition of speech in simulated military environments. The task had some unique challenges, including segmentation of foreground speech from noisy background, the need for robust acoustic models to handle noisy speech, and development of language models from limited training data. In developing the SRI evaluation system for this task, we addressed each of these challenges using a combination of state-of-the-art techniques, including several types of feature normalization, model adaptation, class-based language modeling, multi-pass segmentation and recognition, and word posterior-based decoding and system combination.

UR - http://www.scopus.com/inward/record.url?scp=84946807902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946807902&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84946807902

SP - 1577

EP - 1580

BT - 7th International Conference on Spoken Language Processing, ICSLP 2002

PB - International Speech Communication Association

ER -