Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Text-Independent Cross-Language Voice Conversion

David Sündermann (1,2), Harald Höge (1), Antonio Bonafonte (2), Hermann Ney (3), Julia Hirschberg (4)

(1) Siemens AG, Germany; (2) Universitat Politècnica de Catalunya, Spain; (3) RWTH Aachen University, Germany; (4) Columbia University, USA

So far, cross-language voice conversion requires at least one bilingual speaker and parallel speech data to perform the training. This paper shows how these obstacles can be overcome by means of a recently presented text-independent training method based on unit selection. The new method is evaluated in the framework of the European speech-to-speech translation project TC-Star and achieves a performance similar to that of text-dependent intra-lingual voice conversion.

Full Paper

Bibliographic reference.  Sündermann, David / Höge, Harald / Bonafonte, Antonio / Ney, Hermann / Hirschberg, Julia (2006): "Text-independent cross-language voice conversion", In INTERSPEECH-2006, paper 1665-Thu1BuP.4.