Roles of the average voice in speaker-adaptive HMM-based speech synthesis

In speaker-adaptive HMM-based speech synthesis, there are a few speakers whose 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 found that as mel-cepstral distance from the average voice becomes larger, the MOS scores generally become worse. Although the negative correlation obtained is not strong enough, this helps us improve the training and adaptation strategies for average voice models. Furthermore we remark that this correlation is strongly linked to "vocal attractiveness."

• Type: Journal
• Year: 2010
• Where: INTERSPEECH
• Authors: Junichi Yamagishi, Oliver Watts, Simon King, Bela Usabaev
• Keywords: Average Voice, Average Voice Models, INTERSPEECH 2010, Signal Processing, Speaker-adaptive Hmm-based Speech