8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A First Step Towards Text-Independent Voice Conversion

Hermann Ney (1), David Suendermann (2), Antonio Bonafonte (2), Harald Hoege (3)

(1) RWTH Aachen, Germany
(2) Universitat Politecnica de Catalunya (UPC), Spain
(3) Siemens AG, Germany

So far, all conventional voice conversion approaches are text-dependent, i.e., they need equivalent training utterances of source and target speaker. Since several recently proposed applications call for renouncing this requirement, in this paper, we present an algorithm which finds corresponding time frames within text-independent training data. The performance of this algorithm is tested by means of a voice conversion framework based on linear transformation of the spectral envelope. Experimental results are reported on a Spanish cross-gender corpus utilizing several objective error measures.

Full Paper

Bibliographic reference.  Ney, Hermann / Suendermann, David / Bonafonte, Antonio / Hoege, Harald (2004): "A first step towards text-independent voice conversion", In INTERSPEECH-2004, 1173-1176.