Speech enhancement using a structured codebook

D.H.R. Naidu, S. Srinivasan, G.V.P. Rao

Research output: Contribution to journalArticleAcademicpeer-review


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. In this paper, a method that identifies and performs only relevant likelihood computations by imposing a hierarchical structure on the speech codebook is proposed. The performance of the proposed method is shown to be close to that of the original scheme but at a significantly lower computational cost.
Original languageEnglish
Pages (from-to)EL329-EL335
Number of pages7
JournalJournal of the Acoustical Society of America
Issue number4
Publication statusPublished - 2012


Dive into the research topics of 'Speech enhancement using a structured codebook'. Together they form a unique fingerprint.

Cite this