NDLI: Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features

Content Provider	IEEE Xplore Digital Library
Author	Kubo, Y. Hori, T. Nakamura, A.
Copyright Year	2013
Description	Author affiliation: NTT Commun. Sci. Labs., NTT Corp., Keihanna Science City, Japan (Kubo, Y.; Hori, T.; Nakamura, A.)
Abstract	Recently, structured classification approaches have been considered important with a view to achieving unified modeling of the acoustic and linguistic aspects of speech recognizers. With these approaches, unified representation is achieved by directly optimizing a score function that measures the correspondence between the input and output of the system. Since structured classifiers typically employ a linear function as a score function, extracting expressive features from the input and output of the system is very important. On the other hand, the effectiveness of deep neural networks has been verified by several experiments, and it has been suggested that the outputs of hidden layers in deep neural networks (DNNs) are essential speech features that purely express phonetic information. In this paper, we propose a method for structured classification with DNN features. The proposed method expands conventional DNN- based acoustic models so that they optimizes the weight terms of the arcs in a decoding WFST, which is constructed with the on-the-fly composition method. Since DNN-based features can be considered enhancements in the input representation, the enhancements in the output representation based on the WFST arcs are expected to complement the DNN-based features. The proposed method achieved an 8 % relative error reduction even compared with a strong acoustic model based on DNNs.
Starting Page	7629
Ending Page	7633
File Size	130479
Page Count	5
File Format	PDF
ISBN	9781479903566
ISSN	15206149
DOI	10.1109/ICASSP.2013.6639147
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-05-26
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hidden Markov models Speech recognition Acoustics Speech Training Cost function Linear programming deep neural networks weighed finite-state transducers structured classification
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

Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition

Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition

A study of large vocabulary speech recognition decoding using finite-state graphs

Optimized large vocabulary WFST speech recognition system

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

Efficient WFST-Based One-Pass Decoding With On-The-Fly Hypothesis Rescoring in Extremely Large Vocabulary Continuous Speech Recognition

Improvements on bottleneck feature for large vocabulary continuous speech recognition

A synchronized pruning composition algorithm of weighted finite state transducers for large vocabulary speech recognition

Speaker adaptation of context dependent deep neural networks

Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features

Similar Documents

Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition

Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition

A study of large vocabulary speech recognition decoding using finite-state graphs

Optimized large vocabulary WFST speech recognition system

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

Efficient WFST-Based One-Pass Decoding With On-The-Fly Hypothesis Rescoring in Extremely Large Vocabulary Continuous Speech Recognition

Improvements on bottleneck feature for large vocabulary continuous speech recognition

A synchronized pruning composition algorithm of weighted finite state transducers for large vocabulary speech recognition

Speaker adaptation of context dependent deep neural networks

Large vocabulary continuous speech recognition based on WFST structured classifiers and deep bottleneck features