AA SPECTRAL SPACE WARPING APPROACH TO CROSS-LINGUAL VOICE TRANSFORMATION IN HMM-BASED TTS
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited
Web of Science2WOS source URL (as at 21/05/2020) Click here for the latest count

Other information
AbstractThis paper presents a new approach to cross-lingual voice transformation in HMM-based TTS with only the recordings from two monolingual speakers in different languages (e. g. Mandarin and English). We aim to synthesize one speaker's speech in the other language. We regard the spectral space of any speaker to be composed of universal elementary units (i. e. tied-states) of speech in different languages. Our approach first forces the spectral spaces of the two speakers to have the same number of tied-states. Then we find an optimal one-to-one tied-state mapping between the two spectral spaces. Hence, the mapped speech trajectory in the spectral space of the target speaker can be found according to that generated in the spectral space of the reference speaker. Consequently, we can synthesize high-quality speech for the target monolingual speaker's voice in the other language. This can also be used as training data for a new TTS system.
All Author(s) ListWang H, Soong F, Meng HL
Name of Conference40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Start Date of Conference19/04/2014
End Date of Conference24/04/2014
Place of ConferenceBrisbane
Country/Region of ConferenceAustralia
Detailed descriptionorganized by IEEE Signal Processing Society,
Year2015
Month1
Day1
PublisherIEEE
Pages4874 - 4878
eISBN978-1-4673-6997-8
ISSN1520-6149
LanguagesEnglish-United Kingdom
Keywordscross-lingual; HMM-based TTS; spectral space warping; voice transformation
Web of Science Subject CategoriesAcoustics; Engineering; Engineering, Electrical & Electronic

Last updated on 2020-21-05 at 23:48