The MAP-SPACE denoising algorithm for noise robust speech recognition

We present a new and simple algorithm (MAP-SPACE) for robust speech recognition which can be seen as an hybrid approach between a denoising and an adaptation technique. This algorithm first models clean and noisy training speech using GMMs and then build a denoiser which depends only on the GMMs par...

Full description

Saved in:
Bibliographic Details
Published inIEEE Workshop on Automatic Speech Recognition and Understanding, 2005 pp. 349 - 352
Main Authors Daoudi, K., Cerisara, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Acoustic noise
Automatic speech recognition
Hidden Markov models
Noise reduction
Noise robustness
Signal processing
Signal processing algorithms
Speech enhancement
Speech recognition
Working environment noise
Online AccessGet full text

Cover

More Information
Summary:We present a new and simple algorithm (MAP-SPACE) for robust speech recognition which can be seen as an hybrid approach between a denoising and an adaptation technique. This algorithm first models clean and noisy training speech using GMMs and then build a denoiser which depends only on the GMMs parameters. Given observations in a new environment, the noisy speech GMM is adapted and the parameters of the adapted GMM are then used in the denoiser to compute clean feature estimates. The MAP-SPACE algorithm requires in principle relatively few adaptation data, does not require transcription and does not make any assumption on the corrupting noise. We report preliminary experiments on the Aurora2 database. The results show that MAP-SPACE achieves very good performances, sometimes approaching those of the matched models, in both SNR and noise type mismatch conditions
ISBN:078039478X
9780780394780
DOI:10.1109/ASRU.2005.1566483