Uniform speech parameterization for multi-form segment synthesis

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2011, Pages 337-340

  Sorin, Alexander ^a   Shechtman, Slava ^a   Pollet, Vincent ^b  

^a IBM HAIFA RESEARCH LAB   (Israel)

^b NUANCE COMMUNICATIONS   (United States)

Author keywords

Mel regularized cepstrum; Multi form segment; Speech parameterization; Speech synthesis; Statistical speech synthesis; Text to speech

Indexed keywords

CEPSTRUM; ENHANCEMENT TECHNIQUES; MATHEMATICAL ABSTRACTION; MODEL SEGMENT; MULTI-FORM SEGMENT; PARAMETERIZATION SCHEMES; PHASE SPECTRA; SPEECH SEGMENTS; SPEECH WAVEFORMS; STATISTICAL MODELS; TEXT TO SPEECH; WAVE FORMS;

SPEECH SYNTHESIS;

SPEECH PROCESSING;

EID: 84865718211     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Hunt, A. and Black, A., "Unit selection in a concatenative speech system using a large speech database", in Proc. ICASSP, 1996.
2. Black, A., Zen H. and Tukoda K., "Statistical parametric speech synthesis", in ICASSP, 2007.
3. Pollet, V. and Breen, A., "Synthesis by generation and concatenation of multiform segments", in Proc. Interspeech 2008.
4. Chazan, D., Hoory, R., Sagi, A., Shechtman, S., Sorin, A., Shuang, Z. and Bakis, R., "High quality sinusoidal modeling of wideband speech for the purpose of speech synthesis and modification", In Proc. ICASSP 2006.
5. Shechtman, S. and Sorin, A., "Sinusoidal model parameterization for HMM-based TTS system", in Proc. Interspeech 2010.
6. Chazan, D., Hoory, R., Kons, Z, Silberstein, D, Sorin, A., "Reducing the footprint of the IBM trainable speech synthesis system", In Proc. ICSLP 2002.