NDLI: Modeling disfluency and background events in ASR for a natural language understanding task

Content Provider	IEEE Xplore Digital Library
Author	Rose, R.C. Riccardi, G.
Copyright Year	1999
Description	Author affiliation: Res. Dept., AT&T Bell Labs., Florham Park, NJ, USA (Rose, R.C.)
Abstract	This paper investigates techniques for minimizing the impact of non-speech events on the performance of large vocabulary continuous speech recognition (LVCSR) systems. An experimental study is presented that investigates whether the careful manual labeling of disfluency and background events in conversational speech can be used to provide an additional level of supervision in training HMM acoustic models and statistical language models. First, techniques are investigated for incorporating explicitly labeled disfluency and background events directly into the acoustic HMM. Second, phrase-based statistical language models are trained from utterance transcriptions which include labeled instances of these events. Finally, it is shown that significant word accuracy and run-time performance improvements are obtained for both sets of techniques on a telephone-based spoken language understanding task.
Starting Page	341
Ending Page	344
File Size	525121
Page Count	4
File Format	PDF
ISBN	0780350413
ISSN	15206149
DOI	10.1109/ICASSP.1999.758132
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	1999-03-15
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Automatic speech recognition Natural languages Hidden Markov models Labeling Background noise Vocabulary Speech enhancement Information analysis Runtime Manuals
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Understanding speech understanding

ASR for Romanian Language

Thai Speech Keyword Spotting using Heterogeneous Acoustic Modeling

ProtoLOGOS, system for Romanian language automatic speech recognition and understanding (ASRU)

Integration of utterance verification with statistical language modeling and spoken language understanding

Methodologies for language modeling and search in continuous speech recognition

Developing high performance asr in the IBM multilingual speech-to-speech translation system

Experimenting natural-language dictation with a 20000-word speech recognizer

Improving analysis techniques for automatic speech recognition

Modeling disfluency and background events in ASR for a natural language understanding task

Similar Documents

Understanding speech understanding

ASR for Romanian Language

Thai Speech Keyword Spotting using Heterogeneous Acoustic Modeling

ProtoLOGOS, system for Romanian language automatic speech recognition and understanding (ASRU)

Integration of utterance verification with statistical language modeling and spoken language understanding

Methodologies for language modeling and search in continuous speech recognition

Developing high performance asr in the IBM multilingual speech-to-speech translation system

Experimenting natural-language dictation with a 20000-word speech recognizer

Improving analysis techniques for automatic speech recognition

Modeling disfluency and background events in ASR for a natural language understanding task