Speech enhancement using a structured codebook.


Codebook-based speech enhancement methods that use trained codebooks of speech and noise spectra provide good performance even under non-stationary noise conditions. A drawback, however, is their high computational cost. For every pair of speech and noise codebook vectors, a likelihood score indicating how well that pair matches the observation is computed… (More)
DOI: 10.1121/1.4751987

Cite this paper

@article{Naidu2012SpeechEU, title={Speech enhancement using a structured codebook.}, author={Devireddy Rao Naidu and Sriram Srinivasan and G. V. Prabhakara Rao}, journal={The Journal of the Acoustical Society of America}, year={2012}, volume={132 4}, pages={EL329-35} }