Efficient Adaptation of TTS Duration Model to New Speakers

This paper discusses a methodology using a minimal set of sentences to adapt an existing TTS duration model to capture inter-speaker variations. The assumption is that the original duration database contains information of both language-specific and speaker-specific duration characteristics. In training a duration model for a new speaker, only the speaker-specific information needs to be modeled, therefore the size of the training data can be reduced drastically. Results from several experiments are compared and discussed.