Edinburgh Research Explorer

Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis

Research output: Contribution to journalArticle

Related Edinburgh Organisations

Original languageEnglish
Pages (from-to)420-437
Number of pages18
JournalComputer Speech and Language
Volume27
Issue number2
Early online date17 Sep 2011
DOIs
Publication statusPublished - Feb 2013

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.

    Research areas

  • Speech-to-speech translation, Cross-lingual speaker adaptation, HMM-based speech synthesis

Download statistics

No data available

ID: 4969501