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

Venkata Ramana Rao Gadde; Andreas Stolcke; Dimitra Vergyri; Jing Zheng; Kemal Sonmez; Anand Venkataraman

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

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

Research output: Contribution to conference › Paper › peer-review

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 language	English (US)
Pages	1577-1580
Number of pages	4
State	Published - 2002
Externally published	Yes
Event	7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, United States Duration: Sep 16 2002 → Sep 20 2002

Other

Other	7th International Conference on Spoken Language Processing, ICSLP 2002
Country/Territory	United States
City	Denver
Period	9/16/02 → 9/20/02

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

@conference{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 Kemal Sonmez and Anand Venkataraman",

year = "2002",

language = "English (US)",

pages = "1577--1580",

note = "7th International Conference on Spoken Language Processing, ICSLP 2002 ; Conference date: 16-09-2002 Through 20-09-2002",

}

TY - CONF

T1 - Building an ASR system for Noisy environments

T2 - 7th International Conference on Spoken Language Processing, ICSLP 2002

AU - Gadde, Venkata Ramana Rao

AU - Stolcke, Andreas

AU - Vergyri, Dimitra

AU - Zheng, Jing

AU - Sonmez, 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 - Paper

AN - SCOPUS:84946807902

SP - 1577

EP - 1580

Y2 - 16 September 2002 through 20 September 2002

ER -

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

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this