NDLI: Auto-encoder bottleneck features using deep belief networks

Content Provider	IEEE Xplore Digital Library
Author	Sainath, T.N. Kingsbury, B. Ramabhadran, B.
Copyright Year	2012
Description	Author affiliation: IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, USA (Sainath, T.N.; Kingsbury, B.; Ramabhadran, B.)
Abstract	Neural network (NN) bottleneck (BN) features are typically created by training a NN with a middle bottleneck layer. Recently, an alternative structure was proposed which trains a NN with a constant number of hidden units to predict output targets, and then reduces the dimensionality of these output probabilities through an auto-encoder, to create auto-encoder bottleneck (AE-BN) features. The benefit of placing the BN after the posterior estimation network is that it avoids the loss in frame classification accuracy incurred by networks that place the BN before the softmax. In this work, we investigate the use of pre-training when creating AE-BN features. Our experiments indicate that with the AE-BN architecture, pre-trained and deeper NNs produce better AE-BN features. On a 50-hour English Broadcast News task, the AE-BN features provide over a 1% absolute improvement compared to a state-of-the-art GMM/HMM with a WER of 18.8% and pre-trained NN hybrid system with a WER of 18.4%. In addition, on a larger 430-hour Broadcast News task, AE-BN features provide a 0.5% absolute improvement over a strong GMM/HMM baseline with a WER of 16.0%. Finally, system combination with the GMM/HMM baseline and AE-BN systems provides an additional 0.5% absolute on 430 hours over the AE-BN system alone, yielding a final WER of 15.0%.
Starting Page	4153
Ending Page	4156
File Size	89652
Page Count	4
File Format	PDF
ISBN	9781467300452
ISSN	15206149
e-ISBN	9781467300469
e-ISBN	9781467300445
DOI	10.1109/ICASSP.2012.6288833
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2012-03-25
Publisher Place	Japan
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Hidden Markov models Feature extraction Training Speech Acoustics Artificial neural networks Adaptation models Speech Recognition Deep Belief Networks
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

Extracting deep bottleneck features using stacked auto-encoders

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

Extracting deep neural network bottleneck features using low-rank matrix factorization

Lattice based optimization of bottleneck feature extractor with linear transformation

Multiple time-span feature fusion for deep neural network modeling

Extracting deep bottleneck features for visual speech recognition

But neural network features for spontaneous Vietnamese in BABEL

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

Query-by-example spoken term detection using bottleneck feature and Hidden Markov model

Auto-encoder bottleneck features using deep belief networks

Similar Documents

Extracting deep bottleneck features using stacked auto-encoders

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

Extracting deep neural network bottleneck features using low-rank matrix factorization

Lattice based optimization of bottleneck feature extractor with linear transformation

Multiple time-span feature fusion for deep neural network modeling

Extracting deep bottleneck features for visual speech recognition

But neural network features for spontaneous Vietnamese in BABEL

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

Query-by-example spoken term detection using bottleneck feature and Hidden Markov model

Auto-encoder bottleneck features using deep belief networks