logo Idiap Research Institute        
 [BibTeX] [Marc21]
Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis
Type of publication: Journal paper
Citation: Dines_CSL_2011
Publication status: Accepted
Journal: Computer Speech and Language
Year: 2011
URL: http://www.sciencedirect.com/s...
DOI: doi:10.1016/j.csl.2011.08.003
Abstract: In this paper we present results of unsupervised cross-lingual speaker adaptation applied to text-to-speech synthesis. The application of our research is the personalisation of speech-to-speech translation in which we employ a HMM statistical framework for both speech recognition and synthesis. This framework provides a logical mechanism to adapt synthesised speech output to the voice of the user by way of speech recognition. In this work we present results of several different unsupervised and cross-lingual adaptation approaches as well as an end-to-end speaker adaptive speech-to-speech translation system. Our experiments show that we can successfully apply speaker adaptation in both unsupervised and cross-lingual scenarios and our proposed algorithms seem to generalise well for several language pairs. We also discuss important future directions including the need for better evaluation metrics.
Keywords: cross-lingual speaker adaptation, Machine Translation, speech recognition, speech synthesis
Projects Idiap
Authors Dines, John
Liang, Hui
Saheer, Lakshmi
Gibson, Matthew
Byrne, William
Oura, Keiichiro
Tokuda, Keiichi
Yamagishi, Junichi
King, Simon
Wester, Mirjam
Hirsimäki, Teemu
Karhila, Reima
Kurimo, Mikko
Added by: [UNK]
Total mark: 0
  • Dines_CSL_2011.pdf
       (Version prior to proofing.)