Title | ||
---|---|---|
PHMM based asynchronous acoustic model for Chinese large vocabulary continuous speech recognition |
Abstract | ||
---|---|---|
In this paper, we presented an asynchronous multiple stream based Chinese tonal acoustic modeling framework. In this framework, toneless phonetic units and tones are modeled separately with different acoustic features. During the training and decoding process, a set of models are coupled together with a product hidden Markov models (PHMM) to represent whole tonal phonetic units. Through this, a compound context dependent tonal model can be generated from a few simple models. Experiments show that such model scheme generates more compact and accurate model presentation and brings improvement on the performance for large vocabulary speech recognition tasks. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICASSP.2009.4960624 | ICASSP |
Keywords | Field | DocType |
different acoustic feature,large vocabulary continuous speech,product hidden markov models,speech recognition,accurate model presentation,decoding process,simple model,dependent tonal model,vocabulary,tonal phonetic units,markov model,asynchronous multiple stream,toneless phonetic unit,compound context dependent tonal model,model scheme,multiple stream,acoustic signal processing,phmm,chinese large vocabulary continuous speech recognition,tonal language,chinese tonal acoustic modeling,asynchronous acoustic model,hidden markov models,whole tonal phonetic unit,chinese tonal acoustic modeling framework,context modeling,context dependent,automatic speech recognition,hidden markov model,computational modeling,feature extraction,decoding,parameter estimation,mel frequency cepstral coefficient | Mel-frequency cepstrum,Vocabulary speech recognition,Computer science,Context model,Artificial intelligence,Natural language processing,Asynchronous communication,Pattern recognition,Speech recognition,Decoding methods,Hidden Markov model,Vocabulary,Acoustic model | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4244-2354-5 | 978-1-4244-2354-5 | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wu Hao | 1 | 50 | 37.39 |
Xihong Wu | 2 | 279 | 53.02 |
Huisheng Chi | 3 | 211 | 22.81 |