An extended experimental investigation of DNN uncertainty propagation for noise robust ASRReport as inadecuate

An extended experimental investigation of DNN uncertainty propagation for noise robust ASR - Download this document for free, or read online. Document in PDF available to download.

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery 2 UGR - Universidad de Granada

Abstract : Automatic speech recognition ASR in noisy environments remains a challenging goal. Recently, the idea of estimating the uncertainty about the features obtained after speech enhancement and propagating it to dynamically adapt deep neural network DNN based acoustic models has raised some interest. However, the results in the literature were reported on simulated noisy datasets for a limited variety of uncertainty estimators. We found that they vary significantly in different conditions. Hence, the main contribution of this work is to assess DNN uncertainty decoding performance for different data conditions and different uncertainty estimation-propagation techniques. In addition, we propose a neural network based uncertainty estima-tor and compare it with other uncertainty estimators. We report detailed ASR results on the CHiME-2 and CHiME-3 datasets. We find that, on average, uncertainty propagation provides similar relative improvement on real and simulated data and that the proposed uncertainty estimator performs significantly better than the one in 1. We also find that the improvement is consistent, but it depends on the signal-to-noise ratio SNR and the noise environment.

Keywords : Robust ASR acoustic modeling DNN uncertainty estimation uncertainty propagation

Author: Karan Nathwani - Juan Morales-Cordovilla - Sunit Sivasankaran - Irina Illina - Emmanuel Vincent -



Related documents