Mapping frames with DNN-HMM recognizer for non-parallel voice conversion
Authors:
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 22, 488-494
Abstract
To convert one speaker's voice to another's, the mapping of the corresponding speech segments from source speaker to target speaker must be obtained first. In parallel voice conversion, normally dynamic time warping (DTW) method is used to align signals of source and target voices. However, for conversion between non-parallel speech data, the DTW based mapping method does not work. In this paper, we propose to use a DNN-HMM recognizer to recognize each frame for both source and target speech signals. The vector of pseudo likelihood is then used to represent the frame. Similarity between two frames is measured with the distance between the vectors. A clustering method is used to group both source and target frames. Frame mapping from source to target is then established based on the clustering result. The experiments show that the proposed method can generate similar conversion results compared to parallel voice conversion.Keywords
This publication has 23 references indexed in Scilit:
- Exemplar-Based Sparse Representation With Residual Compensation for Voice ConversionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Non-parallel training for voice conversion based on adaptation method2013
- Text-independent voice conversion based on state mapped codebook2008
- Voice conversion through vector quantization2003
- On the transformation of the speech spectrum for voice conversion2002
- Speaker transformation using sentence HMM based alignments and detailed prosody modification2002
- Speaker Transformation Algorithm using Segmental Codebooks (STASC)Speech Communication, 1999
- Continuous probabilistic transform for voice conversionIEEE Transactions on Speech and Audio Processing, 1998
- Acoustic characteristics of speaker individuality: Control and conversionSpeech Communication, 1995
- Transformation of formants for voice conversion using artificial neural networksSpeech Communication, 1995