Incorporating a mixed excitation model and postfilter into HMM-based text-to-speech synthesis

Systems and Computers in Japan

Volumn 36, Issue 12, 2005, Pages 43-50

  Yoshimura, Takayoshi ^a,d   Tokuda, Keiichi ^b,e   Masuko, Takashi ^c,f,g   Kobayashi, Takao ^c,e,h   Kitamura, Tadashi ^b,e,i  

^a Rd Management Section   (Japan)

^b NAGOYA INSTITUTE OF TECHNOLOGY   (Japan)

^c TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

^d Acoustical Society of   (Japan)

^e IPSJ   (Japan)

^f TOSHIBA CORPORATION   (Japan)

^g IEEE   (Japan)

^h Toshiba Corporate R and D Center ^*

ⁱ Graduate School   (United Kingdom)

Author keywords

Hidden Markov model; Mel ceptral analysis and synthesis; Mixed excitation model; Postfilter; Text to speech synthesis

Indexed keywords

HIDDEN MARKOV MODEL; MEL-CEPTRAL ANALYSIS AND SYNTHESIS; MIXED EXCITATION MODEL; POSTFILTERS; TEXT-TO-SPEECH SYNTHESIS;

MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH CODING;

SPEECH SYNTHESIS;

EID: 27144515530     PISSN: 08821666     EISSN: None     Source Type: Journal    
DOI: 10.1002/scj.20354     Document Type: Article

References (9)

1. Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T. Simultaneous modeling of spectra, pitch and duration in HMM-based speech synthesis. Trans IEICE 2000;J83-D-II:2099-2107.
2. Tokuda K, Yoshimura T, Masuko T, Kobayashi T, Kitamura T. Speech parameter generation algorithms for HMM-based speech synthesis. Proc ICASSP 2000;3:1315-1318.
3. Tamura M, Masuko T, Tokuda K, Kobayashi T. Text-to-speech synthesis with arbitrary speaker's voice from average voice. Proc EUROSPEECH, p 345-348, 2001.
4. McCree AV, Barnwell TP III. A mixed excitation LPC vocoder model for low bit rate speech coding. IEEE Trans Speech Audio Process 1995;3:242-250.
5. Lin W, Koh SN, Lin X. Mixed excitation linear prediction coding of wideband speech at 8 kbps. Proc ICASSP 2000;2:1137-1140.
6. Aoki N, Takaya K, Aoki Y, Yamamoto T. Development of a rule-based speech synthesis system for the Japanese language using a MELP vocoder. IEEE Int Symp on Intelligent Signal Processing and Communication Systems, p 702-705, 2000.
7. Koishida K, Tokuda K, Kobayashi T, Imai S. CELP coding based on mel-cepstral analysis. Proc ICASSP 1995; 1:33-36.
8. Tokuda K, Masuko T, Miyazaki N, Kobayashi T. An HMM based on multi-space probability distributions. Trans IEICE 2000;J83-D-II: 1579-1589.
9. Masuko T, Tokuda K, Miyazaki N, Kobayashi T. Pitch pattern generation using an HMM based on multi-space probability distributions. Trans IEICE 2000;J83-D-II: 1600-1609.