Record Details

Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach
 
Creator PATIL, V
JOSHI, S
RAO, P
 
Subject speech recognition
phonetic segmentation
pronunciation scoring
 
Description Correct and temporally accurate phonetic segmentation of speech utterances is important in applications ranging from transcription alignment to pronunciation error detection. Automatic speech recognizers used in these tasks provide insufficient temporal alignment accuracy apart from a recognition performance that is sensitive to accent and style variations from the training data. A two-staged approach combining HMM broad-class recognition with acoustic-phonetic knowledge based refinement is evaluated for phonetic segmentation accuracy in the context of accent and style mismatches with training data.
 
Publisher ISCA-INST SPEECH COMMUNICATION ASSOC
 
Date 2011-10-25T21:26:58Z
2011-12-15T09:12:09Z
2011-10-25T21:26:58Z
2011-12-15T09:12:09Z
2009
 
Type Proceedings Paper
 
Identifier INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5,2523-2526
978-1-61567-692-7
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15825
http://hdl.handle.net/100/2495
 
Source 10th INTERSPEECH 2009 Conference,Brighton, ENGLAND,SEP 06-10, 2009
 
Language English