NDLI: Comparison of syllable-based and phoneme-based DNN-HMM in Japanese speech recognition

Content Provider	IEEE Xplore Digital Library
Author	Seki, H. Yamamoto, K. Nakagawa, S.
Copyright Year	2014
Description	Author affiliation: Dept. of Comput. Sci. & Eng., Toyohashi Univ. of Technol., Toyohashi, Japan (Seki, H.; Yamamoto, K.; Nakagawa, S.)
Abstract	Japanese is syllabic language. Additionally we have studied syllable-based GMM-HMM for Japanese speech recognition. In this paper, we investigate the differences of recognition accuracy using phoneme/syllable-based GMM-HMM and DNN (Deep Neural Network)-HMM. First, we present a comparison of syllable-based and phoneme-based DNN-HMM. Second, we train the tied state left-context dependent syllable DNN-HMM, and compare these three types of modeling method. In the experiment, we obtained a 5% relative gain for WER using left-context syllable DNN-HMM in comparison with a left-context syllable GMM-HMM, and an 11% relative gain for WER using triphone DNN-HMM in comparison with a syllable-based DNN-HMM. Finally, we got results that modeling left-context phoneme has not worked and context independent syllable-based DNN-HMM got the best performance in the experiments, when applied to the ASJ+JNAS corpus, which consists of about 70 hours.
Starting Page	249
Ending Page	254
File Size	461689
Page Count	6
File Format	PDF
ISBN	9781479969845
e-ISBN	9781479951000
DOI	10.1109/ICAICTA.2014.7005949
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-08-20
Publisher Place	Indonesia
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Context Training GMM-HMM Deep neural network Neural networks Hidden Markov models Rectifiers Speech recognition Phoneme DNN-HMM Syllable Context modeling
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

Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

A comparison of Gaussian Mixture Modeling (GMM) and Hidden Markov Modeling (HMM) based approaches for Automatic Phoneme Recognition in Kannada

Turkish Speech Recognition Based On Deep Neural Networks

GMM-free DNN acoustic model training

Multiple time-span feature fusion for deep neural network modeling

Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling

Deep neural networks for syllable based acoustic modeling in Chinese speech recognition

Comparison of Syllable/Phone HMM Based Mandarin TTS

Comparison of syllable-based and phoneme-based DNN-HMM in Japanese speech recognition

Similar Documents

Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

A comparison of Gaussian Mixture Modeling (GMM) and Hidden Markov Modeling (HMM) based approaches for Automatic Phoneme Recognition in Kannada

Turkish Speech Recognition Based On Deep Neural Networks

GMM-free DNN acoustic model training

Multiple time-span feature fusion for deep neural network modeling

Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMS in acoustic modeling

Deep neural networks for syllable based acoustic modeling in Chinese speech recognition

Comparison of Syllable/Phone HMM Based Mandarin TTS

Comparison of syllable-based and phoneme-based DNN-HMM in Japanese speech recognition