@inproceedings{fe0711c922f944d2baeb126b5139c0aa,
title = "Combining multiple high quality corpora for improving HMM-TTS",
abstract = "The most reliable way to build synthetic voices for end-products is to start with high quality recordings from professional voice talents. This paper describes the application of average voice models (AVMs) and a novel application of cluster adaptive training (CAT) to combine a small number of these high quality corpora to make best use of them and improve overall voice quality in hidden Markov model based text-to-speech (HMMTTS) systems. It is shown that integrated training by both CAT and AVM approaches, yields better sounding voices than speaker dependent modelling. It is also shown that CAT has an advantage over AVMs when adapting to a new speaker. Given a limited amount of adaptation data CATmaintains a much higher voice quality even when adapted to tiny amounts of speech.",
keywords = "Average voice models, Cluster adaptive training, Speaker adaptation, Speech synthesis",
author = "Vincent Wan and Javier Latorre and Chin, {K. K.} and Langzhou Chen and Gales, {Mark J.F.} and Heiga Zen and Kate Knill and Masami Akamine",
year = "2012",
language = "English",
isbn = "9781622767595",
series = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",
pages = "1134--1137",
booktitle = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",
note = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 ; Conference date: 09-09-2012 Through 13-09-2012",
}