NDLI: Learning a Discriminative Weighted Finite-State Transducer for Speech Recognition

Content Provider	IEEE Xplore Digital Library
Author	Lehr, M. Shafran, I.
Copyright Year	2006
Abstract	Weighted finite-state transducers (WFSTs) have been widely adopted as efficient representations of a general speech recognition model. The WFST for speech recognizer is typically assembled or composed from the several components-the language model, the pronunciation mapping and the acoustic model-which are estimated separately without any end-to-end optimization. This paper examines how the weights of such transducers can be learned in a manner that captures the interaction between the components. The paths in the transducer are represented as n -grams defined over the input and output sequences whose linear weights are learned using a discriminative criterion. The resulting linear model factors into two weighted finite-state acceptors (WFSAs) which can be applied as corrections to the input and the output side of the initial WFST. This formulation allows duration cues to be incorporated seamlessly. Empirical results on a large vocabulary Arabic GALE task demonstrate that the proposed model improves word error rate substantially, with a gain of 1.5%-1.7% absolute. Through a series of experiments, we analyze the contributions from and interactions between acoustic, duration, and language components to find that duration cues play an important role in a large-vocabulary Arabic speech recognition task. Although this paper focuses on speech recognition, the proposed framework for learning the weights of a finite transducer is more general in nature and can be applied to other tasks such as utterance classification.
Sponsorship	IEEE Signal Processing Society
Starting Page	1360
Ending Page	1367
Page Count	8
File Size	652882
File Format	PDF
ISSN	15587916
Volume Number	19
Issue Number	5
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-07-01
Publisher Place	U.S.A.
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Acoustics Hidden Markov models Speech recognition Transducers Computational modeling Speech Data models learning finite-state transducers Acoustic modeling discriminative learning duration modeling finite-state transducers language modeling
Content Type	Text
Resource Type	Article
Subject	Acoustics and Ultrasonics Electrical and Electronic Engineering

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

Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition

A general discriminative training algorithm for speech recognition using weighted finite-state transducers

WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding

Learning a discriminative weighted finite-state transducer for speech recognition (2011)

Eigentriphones for Context-Dependent Acoustic Modeling

Hidden Markov Acoustic Modeling With Bootstrap and Restructuring for Low-Resourced Languages

Modeling acoustic transitions in speech by modified hidden Markov models with state duration and state duration-dependent observation probabilities

A discriminative model for continuous speech recognition based on Weighted Finite State Transducers

Acoustic Modeling Using Deep Belief Networks

Learning a Discriminative Weighted Finite-State Transducer for Speech Recognition

Similar Documents

Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition

A general discriminative training algorithm for speech recognition using weighted finite-state transducers

WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding

Learning a discriminative weighted finite-state transducer for speech recognition (2011)

Eigentriphones for Context-Dependent Acoustic Modeling

Hidden Markov Acoustic Modeling With Bootstrap and Restructuring for Low-Resourced Languages

Modeling acoustic transitions in speech by modified hidden Markov models with state duration and state duration-dependent observation probabilities

A discriminative model for continuous speech recognition based on Weighted Finite State Transducers

Acoustic Modeling Using Deep Belief Networks

Learning a Discriminative Weighted Finite-State Transducer for Speech Recognition