Abstract | ||
---|---|---|
Most existing voice conversion systems, particularly those based on Gaussian mixture models, require a set of paired acoustic vectors from the source and target speakers to learn their corresponding transformation function. The alignment of phonetically equivalent source and target vectors is not problematic when the training corpus is parallel, which means that both speakers utter the same training sentences. However, in some practical situations, such as cross-lingual voice conversion, it is not possible to obtain such parallel utterances. With an aim towards increasing the versatility of current voice conversion systems, this paper proposes a new iterative alignment method that allows pairing phonetically equivalent acoustic vectors from nonparallel utterances from different speakers, even under cross-lingual conditions. This method is based on existing voice conversion techniques, and it does not require any phonetic or linguistic information. Subjective evaluation experiments show that the performance of the resulting voice conversion system is very similar to that of an equivalent system trained on a parallel corpus. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/TASL.2009.2038669 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
resulting voice conversion system,nonparallel corpus,parallel utterance,training voice conversion systems,inca algorithm,voice conversion technique,phonetically equivalent acoustic vector,nonparallel corpora,current voice conversion system,parallel corpus,training voice conversion system,phonetically equivalent source,cross-lingual voice conversion,existing voice conversion system,equivalent system,signal analysis,helium,speech recognition,transformation function,gaussian processes,iterative methods,loudspeakers,signal processing,government,gaussian mixture model,speech synthesis | Speech enhancement,Rule-based machine translation,Signal processing,Speech synthesis,Transformation (function),Computer science,Iterative method,Speech recognition,Artificial intelligence,Natural language processing,Loudspeaker,Mixture model | Journal |
Volume | Issue | ISSN |
18 | 5 | 1558-7916 |
Citations | PageRank | References |
39 | 1.29 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Erro | 1 | 169 | 6.24 |
Asunción Moreno | 2 | 399 | 44.97 |
Antonio Bonafonte | 3 | 693 | 64.80 |