Paper Info
Title
HMM/ANN system for vietnamese continuous digit recognition
Abstract
The study of a system for Vietnamese continuous digit recognition is described. The CSLU Toolkit was used to develop and implement hybrid HMM/ANN recognition systems. Experiments were done with a corpus of 442 sentences with 2340 words, which were extracted from two telephone-speech corpora: "22 Language v1.2" and "Multi-Language Telephone Speech v1.2". In our experiments, a context-dependent phoneme recognizer has achieved better recognition performance than a context-dependent demi-syllable recognizer and a context-independent phoneme recognizer. Among feature sets applied to the context-dependent phoneme recognizer, the set of 12 PLP features with CMS, energy and corresponding delta values has achieved the best recognition result (96.83% word accuracy and 87.67% sentence correct).
Year
DOI
Venue
2003
10.1007/3-540-45034-3_48
international conference on supercomputing
Keywords
Field
DocType
context-dependent phoneme recognizer,ANN recognition system,Vietnamese continuous digit recognition,best recognition result,better recognition performance,context-dependent demi-syllable recognizer,context-independent phoneme recognizer,Multi-Language Telephone Speech v1,language v1,CSLU Toolkit,ANN system,vietnamese continuous digit recognition
Computer science,Markov model,Phrase,Speech recognition,Natural language processing,Syllable,Artificial intelligence,Digit recognition,Vietnamese,Artificial neural network,Hidden Markov model,Sentence
Conference
Volume
ISSN
ISBN
2718
0302-9743
3-540-40455-4
Citations 
PageRank 
References 
2
0.40
2
Authors
4
Name
Order
Citations
PageRank
Dang Ngoc Duc120.40
John-Paul Hosom223123.43
Luong Chi Mai3224.54
Thang Vu Tat420.40