11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Roles of the Average Voice in Speaker-Adaptive HMM-Based Speech Synthesis

Junichi Yamagishi (1), Oliver Watts (1), Simon King (1), Bela Usabaev (2)

(1) University of Edinburgh, UK
(2) Universität Tübingen, Germany

In speaker-adaptive HMM-based speech synthesis, there are typically a few speakers for which the output synthetic speech sounds worse than that of other speakers, despite having the same amount of adaptation data from within the same corpus. This paper investigates these fluctuations in quality and concludes that as mel-cepstral distance from the average voice becomes larger, the MOS naturalness scores generally become worse. Although this negative correlation is not that strong, it suggests a way to improve the training and adaptation strategies. We also draw comparisons between our findings and the work of other researchers regarding "vocal attractiveness."'

Full Paper

Bibliographic reference.  Yamagishi, Junichi / Watts, Oliver / King, Simon / Usabaev, Bela (2010): "Roles of the average voice in speaker-adaptive HMM-based speech synthesis", In INTERSPEECH-2010, 418-421.