NDLI: Structurally discriminative graphical models for automatic speech recognition - results from the 2001 Johns Hopkins Summer Workshop

Content Provider	IEEE Xplore Digital Library
Author	Zweig, G. Bilmes, J. Richardson, T. Filali, K. Livescu, K. Xu, P. Jackson, K. Brandman, Y. Sandness, E. Holtz, E. Torres, J. Byrne, B.
Copyright Year	2002
Description	Author affiliation: Speech Works, Boston MA, 02111, USA (Sandness, E.) \|\| Harvard University, Cambridge MA, 02138, USA (Holtz, E.) \|\| University of Washington, Seattle, 98195, USA (Bilmes, J.; Richardson, T.; Filali, K.) \|\| Johns Hopkins University, Baltimore MD, 21218, USA (Xu, P.; Byrne, B.) \|\| IBM T. J. Watson Research Center, Yorktown Heights, NY, 10598, USA (Zweig, G.) \|\| Stanford University, CA, 94305, USA (Torres, J.) \|\| U.S. Department of Defense, Ft. Meade MD, 20755, USA (Jackson, K.) \|\| Massachusetts Institute of Technology, Cambridge, 02139, USA (Livescu, K.) \|\| Phonetact Inc., Los Altos CA, 94002, USA (Brandman, Y.)
Abstract	In recent years there has been growing interest in discriminative parameter training techniques, resulting from notable improvements in speech recognition performance on tasks ranging in size from digit recognition to Switchboard. Typified by Maximum Mutual Information training, these methods assume a fixed statistical modeling structure, and then optimize only the associated numerical parameters (such as means, variances, and transition matrices). In this paper, we explore the significantly different methodology of discriminative structure learning. Here, the fundamental dependency relationships between random variables in a probabilistic model are learned in a discriminative fashion, and are learned separately from the numerical parameters. Tn order to apply the principles of structural discriminability, we adopt the framework of graphical models, which allows an arbitrary set of variables with arbitrary conditional independence relationships to be modeled at each time frame. We present results using a new graphical modeling toolkit (described in a companion paper) from the recent 2001 Johns Hopkins Summer Workshop. These results indicate that significant gains result from discriminative structural analysis of both conventional MFCC and novel AM-FM features on the Aurora continuous digits task.
File Size	2188559
File Format	PDF
ISBN	0780374029
ISSN	15206149
DOI	10.1109/ICASSP.2002.5743662
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2002-05-13
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hidden Markov models Q measurement Conferences Frequency modulation Equations Contracts Bayesian methods
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