Details

Autor(en) / Beteiligte

• Yamagishi, J.
• Nose, T.
• Zen, H.
• Zhen-Hua Ling
• Toda, T.
• Tokuda, K.
• King, S.
• Renals, S.

Titel

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Ist Teil von

• IEEE transactions on audio, speech, and language processing, 2009-08, Vol.17 (6), p.1208-1230

Ort / Verlag

Piscataway, NJ: IEEE

Erscheinungsjahr

2009

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• This paper describes a speaker-adaptive HMM-based speech synthesis system. The new system, called ldquoHTS-2007,rdquo employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available. In addition, a comparison study with several speech synthesis techniques shows the new system is very robust: It is able to build voices from less-than-ideal speech data and synthesize good-quality speech even for out-of-domain sentences.