NDLI: Visualization of continuous density hidden Markov models

Content Provider	IEEE Xplore Digital Library
Author	Kopparapu, S.K.
Copyright Year	2011
Description	Author affiliation: TCS Innovation Labs - Mumbai, Tata Consultancy Services Ltd., Yantra Park, Thane (West), Maharashtra, India - 400601 (Kopparapu, S.K.)
Abstract	Continuous density hidden Markov models (CD-HMMs) are doubly stochastic processes which are extensively used in speech and image signal processing. Especially in case of isolated spoken word recognition systems, the spoken words are usually modeled using HMMs. While CD-HMMs are in extensive use, to most of the speech community the HMMs remain abstract in the sense there has been no nice way of visualizing them. In this paper, we give a visual representation for an HMM. These visuals serve two purposes, (a) they give the beginner in the area of speech technology a feel for the HMMs and (b) the HMMs of words can be visually compared quickly to check if the HMM models of any two words are similar, which could in turn cause confusion during recognition.
Starting Page	1
Ending Page	4
File Size	3841215
Page Count	4
File Format	PDF
ISBN	9781457708930
e-ISBN	9781457708947
DOI	10.1109/ICSPCC.2011.6061651
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-09-14
Publisher Place	China
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Visualization Hidden Markov models Speech recognition Speech Acoustics Speech processing
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

Towards unsupervised speech processing

Recent developments in large vocabulary continuous speech recognition

Hidden Markov Models for automatic speech recognition

Unsupervised submodular subset selection for speech data

Speaking rate dependent multiple acoustic models using continuous frame rate normalization

Multimodal interaction for service robot control

A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition

Large margin hidden Markov models for speech recognition

Continuous Malayalam speech recognition using Hidden Markov Models

Visualization of continuous density hidden Markov models

Similar Documents

Towards unsupervised speech processing

Recent developments in large vocabulary continuous speech recognition

Hidden Markov Models for automatic speech recognition

Unsupervised submodular subset selection for speech data

Speaking rate dependent multiple acoustic models using continuous frame rate normalization

Multimodal interaction for service robot control

A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition

Large margin hidden Markov models for speech recognition

Continuous Malayalam speech recognition using Hidden Markov Models

Visualization of continuous density hidden Markov models