Sciweavers

ICASSP
2011
IEEE

An iterative least-squares technique for dereverberation

12 years 7 months ago
An iterative least-squares technique for dereverberation
Some recent dereverberation approaches that have been effective for automatic speech recognition (ASR) applications, model reverberation as a linear convolution operation in the spectral domain, and derive a factorization to decompose spectra of reverberated speech in to those of clean speech and room-response filter. Typically, a general non-negative matrix factorization (NMF) framework is employed for this. In this work1 we present an alternative to NMF and propose an iterative least-squares deconvolution technique for spectral factorization. We propose an efficient algorithm for this and experimentally demonstrate it’s effectiveness in improving ASR performance. The new method results in 40-50% relative reduction in word error rates over standard baselines on artificially reverberated speech.
Kshitiz Kumar, Bhiksha Raj, Rita Singh, Richard M.
Added 21 Aug 2011
Updated 21 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Kshitiz Kumar, Bhiksha Raj, Rita Singh, Richard M. Stern
Comments (0)