Title
On the recognition of cochlear implant-like spectrally reduced speech with MFCC and HMM-based ASR
Abstract
This correspondence investigates the recognition of cochlear implant-like spectrally reduced speech (SRS) using mel frequency cepstral coefficient (MFCC) and hidden Markov model (HMM)-based automatic speech recognition (ASR). The SRS was synthesized from subband temporal envelopes extracted from original clean test speech, whereas the acoustic models were trained on a different set of original clean speech signals of the same speech database. It was shown that changing the bandwidth of the subband temporal envelopes had no significant effect on the ASR word accuracy. In addition, increasing the number of frequency subbands of the SRS from 4 to 16 improved significantly the system performance. Furthermore, the ASR word accuracy attained with the original clean speech can be achieved by using the 16-, 24-, or 32-subband SRS. The experiments were carried out by using the TI-digits speech database and the HTK speech recognition toolkit.
Year
DOI
Venue
2010
10.1109/TASL.2009.2032945
IEEE Transactions on Audio, Speech & Language Processing
Keywords
Field
DocType
automatic speech recognition,original clean test speech,htk speech recognition toolkit,hmm-based asr,original clean speech,speech database,cochlear implant-like spectrally reduced,cochlear implant-like spectrally,original clean speech signal,ti-digits speech database,32-subband srs,asr word accuracy,subband temporal envelope,speech recognition,speech synthesis,mel frequency cepstral coefficient,hidden markov model,databases,system performance,bandwidth,difference set,hidden markov models
Mel-frequency cepstrum,Speech synthesis,Pattern recognition,Computer science,Speech recognition,Cochlear implant,Bandwidth (signal processing),Acoustic testing,Signal synthesis,Artificial intelligence,Hidden Markov model,Word accuracy
Journal
Volume
Issue
ISSN
18
5
1558-7916
Citations 
PageRank 
References 
2
0.37
7
Authors
3
Name
Order
Citations
PageRank
Cong-Thanh Do1193.94
D. Pastor219323.93
André Goalic3142.84