Exemplar-based speech enhancement for deep neural network based automatic speech recognition

Baby, Deepak; Gemmeke, Jort; Virtanen, Tuomas; Hamme, Hugo Van
Abstract

Deep neural network (DNN) based acoustic modelling has been successfully used for a variety of automatic speech recognition (ASR) tasks, thanks to its ability to learn higher-level information using multiple hidden layers. This paper investigates the recently proposed exemplar-based speech enhancement technique using coupled dictionaries as a pre-processing stage for DNN-based systems. In this setting, the noisy speech is decomposed as a weighted sum of atoms in an input dictionary containing exemplars sampled from a domain of choice, and the resulting weights are applied to a coupled output dictionary containing exemplars sampled in the short-time Fourier transform (STFT) domain to directly obtain the speech and noise estimates for speech enhancement. In this work, settings using input dictionary of exemplars sampled from the STFT, Mel-integrated magnitude STFT and modulation envelope spectra are evaluated. Experiments performed on the AURORA-4 database revealed that these pre-processing stages can improve the performance of the DNN-HMM-based ASR systems with both clean and multi-condition training.

Keywords

coupled dictionaries; deep neural networks; modulation envelope; non-negative matrix factorisation; speech enhancement

Research areas

Year:
2015
Book title:
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages:
4485-4489
Month:
8
ISBN:
9781467369978
DOI:
10.1109/ICASSP.2015.7178819