Speaker and language adaptive training for HMM-based polyglot speech synthesis

This paper proposes a technique for speaker and language adaptive training for HMM-based polyglot speech synthesis. Language-specific context-dependencies in the system are captured using CAT with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by CMLLR-based transforms. This framework allows multi-speaker/multi-language adaptive training and synthesis to be performed. Experimental results show that the proposed technique achieves better synthesis performance than both speaker-adaptively trained language-dependent and languageindependent models.

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Heiga Zen
• Keywords: Adaptive Training, INTERSPEECH 2010, Language Adaptive Training, Polyglot Speech Synthesis, Signal Processing