Proceedings of the KSPS conference (대한음성학회:학술대회논문집)
- 2005.11a
- /
- Pages.67-70
- /
- 2005
GMM based Nonlinear Transformation Methods for Voice Conversion
- Vu, Hoang-Gia (Voice Interface Lab, Div. of Computer Science, EECS., KAIST.) ;
- Bae, Jae-Hyun (Voice Interface Lab, Div. of Computer Science, EECS., KAIST.) ;
- Oh, Yung-Hwan (Voice Interface Lab, Div. of Computer Science, EECS., KAIST.)
- Published : 2005.11.17
Abstract
Voice conversion (VC) is a technique for modifying the speech signal of a source speaker so that it sounds as if it is spoken by a target speaker. Most previous VC approaches used a linear transformation function based on GMM to convert the source spectral envelope to the target spectral envelope. In this paper, we propose several nonlinear GMM-based transformation functions in an attempt to deal with the over-smoothing effect of linear transformation. In order to obtain high-quality modifications of speech signals our VC system is implemented using the Harmonic plus Noise Model (HNM)analysis/synthesis framework. Experimental results are reported on the English corpus, MOCHA-TlMlT.
Keywords