Syllable based continuous speech recognizer with varied length maximum likelihood character segmentation

Speech is the most natural and quick mode of transforming and sharing information. To automate the process of speech production and perception, many researches are carried out for more than five decades. For an Automatic speech Recognition (ASR) of a large or unlimited vocabulary, a recognition unit...

Full description

Saved in:
Bibliographic Details
Main Authors: Ganesh, Akila A., Ravichandran, Chandra
Format: Conference Proceeding
Language:English
Subjects:
Context
Context modeling
Hidden Markov models
Maximum Likelihood (ML) segmentation
Segmentation
Speech
Speech recognition
Syllable
Varied Length Maximum Likelihood Segmentation (VLML)
Vectors
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Speech is the most natural and quick mode of transforming and sharing information. To automate the process of speech production and perception, many researches are carried out for more than five decades. For an Automatic speech Recognition (ASR) of a large or unlimited vocabulary, a recognition unit smaller than word size is necessary. In this paper a new approach for segmenting the input utterance into individual characters is presented. The accuracy of boundary detection of baseline Maximum Likelihood (ML) Algorithm and the proposed algorithm is also compared and discussed.
DOI:10.1109/ICACCI.2013.6637302