ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models

Matthew Gibson

Hidden Markov model (HMM) -based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to firstly estimate the transcription of the adaptation data. By defining a mapping between HMM-based synthesis models and ASR-style models, this paper introduces an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for supplementary acoustic models. Further, this enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data.


doi: 10.21437/Interspeech.2009-151

Cite as: Gibson, M. (2009) Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models. Proc. Interspeech 2009, 1791-1794, doi: 10.21437/Interspeech.2009-151

@inproceedings{gibson09_interspeech,
  author={Matthew Gibson},
  title={{Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1791--1794},
  doi={10.21437/Interspeech.2009-151}
}