ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Performance comparison of HMM and VQ based single channel speech separation

M. H. Radfar, W. -Y. Chan, R. M. Dansereau, W. Wong

In this paper, single channel speech separation (SCSS) techniques based on hidden Markov models (HMM) and vector quantization (VQ) are described and compared in terms of (a) signal-to-noise ratio (SNR) between separated and original speech signals, (b) preference of listeners, and (c) computational complexity. The SNR results show that the HMM-based technique marginally outperforms the VQ-based technique by 0.85 dB in experiments conducted on mixtures of female-female, male-male, and male-female speakers. Subjective tests show that listeners prefer HMM over VQ for 86.70% of test speech files. This improvement, however, is at the expense of a drastic increase in computational complexity when compared with the VQ-based technique.


doi: 10.21437/Interspeech.2009-574

Cite as: Radfar, M.H., Chan, W.-Y., Dansereau, R.M., Wong, W. (2009) Performance comparison of HMM and VQ based single channel speech separation. Proc. Interspeech 2009, 1951-1954, doi: 10.21437/Interspeech.2009-574

@inproceedings{radfar09_interspeech,
  author={M. H. Radfar and W. -Y. Chan and R. M. Dansereau and W. Wong},
  title={{Performance comparison of HMM and VQ based single channel speech separation}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1951--1954},
  doi={10.21437/Interspeech.2009-574}
}