NDLI: Improved hidden Markov model adaptation method for reduced frame rate speech recognition

Content Provider	IET Digital Library
Author	Lee, L. M. Le, H. H. Jean, F. R.
Abstract	An improved hidden Markov model (HMM) adaptation method is proposed for the recognition of reduced frame rate speech. In previous studies of this kind of model adaptation, individual models were first adapted and then the adapted models were connected to form the word network for a speech recognition system. This adapting-then-connecting approach can produce transitions that skip too many states and increase insertion errors. In the proposed new method, the transition probabilities from the states of a HMM to the states of a following model are calculated by first connecting the two models to form a combined model and then adapting the transition probability matrix of the combined model. This connecting-then-adapting approach can rectify the problem of skipping too many states, and therefore reduce insertion errors. Experiments were conducted to investigate the effectiveness of the proposed method and the experimental results show that the proposed new method can obtain better recognition accuracy.
Starting Page	962
Ending Page	964
Page Count	3
ISSN	00135194
Volume Number	53
e-ISSN	1350911X
Issue Number	Issue 14, Jul (2017)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/el/53/14
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/el.2017.0458
Journal	Electronics Letters
Publisher Date	2017-05-31
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Connecting-then-adapting Approach Frame Rate Speech Recognition Hidden Markov Model HMM Adaptation Method Improved Hidden Markov Model Adaptation Method Markov Processes Speech Processing Technique Speech Recognition Speech Recognition And Synthesis
Content Type	Text
Resource Type	Article
Subject	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

Adaptation of Hidden Markov Models for Recognizing Speech of Reduced Frame Rate

Inverse filter based excitation model for HMM-based speech synthesis system

Recognition of packet loss speech using the most reliable reduced-frame-rate data

Adaptation of hidden Markov model mean parameters using two-dimensional PCA with constraint on speaker weight

Comparative study of automatic speech recognition techniques

Speaker adaptation using probabilistic linear discriminant analysis for continuous speech recognition

Recognition of isolated digits using DNN–HMM and harmonic noise model

Optimal state duration assignment in hidden Markov model-based text-to-speech synthesis system

Speech Synthesis Based on Hidden Markov Models

Improved hidden Markov model adaptation method for reduced frame rate speech recognition

Similar Documents

Adaptation of Hidden Markov Models for Recognizing Speech of Reduced Frame Rate

Inverse filter based excitation model for HMM-based speech synthesis system

Recognition of packet loss speech using the most reliable reduced-frame-rate data

Adaptation of hidden Markov model mean parameters using two-dimensional PCA with constraint on speaker weight

Comparative study of automatic speech recognition techniques

Speaker adaptation using probabilistic linear discriminant analysis for continuous speech recognition

Recognition of isolated digits using DNN–HMM and harmonic noise model

Optimal state duration assignment in hidden Markov model-based text-to-speech synthesis system

Speech Synthesis Based on Hidden Markov Models

Improved hidden Markov model adaptation method for reduced frame rate speech recognition