Journal Articles Computer Speech and Language Year : 2017

A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions

Abstract

Robustness to reverberation is a key concern for distant-microphone ASR. Various approaches have been proposed, including single-channel or multichannel dereverberation, robust feature extraction, alternative acoustic models, and acoustic model adaptation. However, to the best of our knowledge, a detailed study of these techniques in varied reverberation conditions is still missing in the literature. In this paper, we conduct a series of experiments to assess the impact of various dereverberation and acoustic model adaptation approaches on the ASR performance in the range of reverberation conditions found in real domestic environments. We consider both established approaches such as WPE and newer approaches such as learning hidden unit contribution (LHUC) adaptations, whose performance has not been reported before in this context, and we employ them in combination. Our results indicate that performing weighted prediction error (WPE) dereverberation on a reverberated test speech utterance and decoding using an deep neural network (DNN) acoustic model trained with multi-condition reverberated speech with feature-space maximum likelihood linear regression (fMLLR) transformed features, outperforms more recent approaches and helps significantly reduce the word error rate (WER).
Fichier principal
Vignette du fichier
sivasankaran_CSL17.pdf (1) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01461382 , version 1 (08-02-2017)

Identifiers

Cite

Sunit Sivasankaran, Emmanuel Vincent, Irina Illina. A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions. Computer Speech and Language, 2017, 46, pp.444-460. ⟨10.1016/j.csl.2017.02.003⟩. ⟨hal-01461382⟩
463 View
576 Download

Altmetric

Share

More