Title
Speech bandwidth extension based on speech phonetic content and speaker vocal tract shape estimation
Abstract
In this paper, we introduce a new speech bandwidth extension (BWE) algorithm which involves phonetic and speaker dependent estimation of the high-band part of the spectral envelope. Speech phoneme information is extracted by using a hidden Markov model. Speaker vocal tract shape information corresponding to the wideband signal is extracted by a codebook search. The proposed method allows better estimation of high-band formant frequencies, especially for voiced sounds, and better estimation of spectral envelope gain, especially for unvoiced sounds. Postprocessing of the estimated vocal tract shape allows artifacts reduction in cases of erroneous estimation of speech phoneme or vocal tract shape. We present experimental results that demonstrate improved wideband quality for different speech sounds in comparison to other BWE methods.
Year
Venue
Keywords
2011
Barcelona
hidden markov models,speech,bwe methods,artifact reduction,hidden markov model,high-band formant frequencies,phonetic dependent estimation,speaker dependent estimation,speaker vocal tract shape estimation,speaker vocal tract shape information,spectral envelope,spectral envelope gain,speech bandwidth extension algorithm,speech phoneme,speech phonetic content,unvoiced sounds,wideband quality,wideband signal,shape,bandwidth,estimation,feature extraction,niobium
Field
DocType
ISSN
Speech processing,Wideband,Spectral envelope,Pattern recognition,Computer science,Voice activity detection,Bandwidth extension,Speech recognition,Artificial intelligence,Formant,Hidden Markov model,Vocal tract
Conference
2076-1465
Citations 
PageRank 
References 
3
0.48
8
Authors
3
Name
Order
Citations
PageRank
Itai Katsir130.48
Israel Cohen21734121.85
David Malah321960.95