A statistical observation model for noisy reverberant speech features and its application to robust ASR

Abstract

In this work, an observation model for the joint compensation of noise and reverberation in the logarithmic mel power spectral density domain is considered. It relates the features of the noisy reverberant speech to those of the non-reverberant speech and the noise. In contrast to enhancement of features only corrupted by reverberation (reverberant features), enhancement of noisy reverberant features requires a more sophisticated model for the error introduced by the proposed observation model. In a first consideration, it will be shown that this error is highly dependent on the instantaneous ratio of the power of reverberant speech to the power of the noise and, moreover, sensitive to the phase between reverberant speech and noise in the short-time discrete Fourier domain. Afterwards, a statistically motivated approach will be presented allowing for the model of the observation error to be inferred from the error model previously used for the reverberation only case. Finally, the developed observation error model will be utilized in a Bayesian feature enhancement scheme, leading to improvements in word accuracy on the AURORA5 database.

5 Figures and Tables

Cite this paper

@article{Leutnant2012ASO, title={A statistical observation model for noisy reverberant speech features and its application to robust ASR}, author={Volker Leutnant and Alexander Krueger and Reinhold H{\"a}b-Umbach}, journal={2012 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2012)}, year={2012}, pages={142-147} }