Title :
Residual prediction based on unit selection
Author :
Sundermann, David ; Hoge, Harald ; Bonafonte, Antonio ; Ney, Hermann ; Black, Alan W.
Author_Institution :
Siemens Corp. Technol., Munich
Abstract :
Recently, we presented a study on residual prediction techniques that can be applied to voice conversion based on linear transformation or hidden Markov model-based speech synthesis. Our voice conversion experiments showed that none of the six compared techniques was capable of successfully converting the voice while achieving a fair speech quality. In this paper, we suggest a novel residual prediction technique based on unit selection that outperforms the others in terms of speech quality (mean opinion score = 3) while keeping the conversion performance
Keywords :
hidden Markov models; speech enhancement; speech synthesis; hidden Markov model; linear transformation; residual prediction techniques; speech quality; speech synthesis; voice conversion; Frequency conversion; Hidden Markov models; Mel frequency cepstral coefficient; Predictive models; Smoothing methods; Speech analysis; Speech recognition; Speech synthesis; Target recognition; Testing;
Conference_Titel :
Automatic Speech Recognition and Understanding, 2005 IEEE Workshop on
Conference_Location :
San Juan
Print_ISBN :
0-7803-9478-X
Electronic_ISBN :
0-7803-9479-8
DOI :
10.1109/ASRU.2005.1566484
