Deep learning for minimum mean-square error approaches to speech enhancement

By Aaron Nicolson, Kuldip K. Paliwal. 2019

128 citations recorded by the source corpus.

Abstract Recently, the focus of speech enhancement research has shifted from minimum mean-square error (MMSE) approaches, like the MMSE short-time spectral amplitude (MMSE-STSA) estimator, to state-of-the-art masking- and mapping-based deep learning approaches. We aim to bridge the gap between these two differing speech enhancement approaches. Deep learning methods for MMSE approaches are investigated in this work, with the objective of producing intelligible enhanced speech at a high quality. Since the speech enhancement performance of an MMSE approach improves with the accuracy of the used a priori signal-to-noise ratio (SNR) estimator, a residual long short-term memory (ResLSTM) network is utilised here to accurately estimate the a priori SNR. MMSE approaches utilising the ResLSTM a priori SNR estimator are evaluated using subjective and objective measures of speech quality and intelligibility. The tested conditions include real-world non-stationary and coloured noise sources at multiple SNR levels. MMSE approaches utilising the proposed a priori SNR estimator are able to achieve higher enhanced speech quality and intelligibility scores than recent masking- and mapping-based deep learning approaches. The results presented in this work show that the performance of an MMSE approach to speech enhancement significantly increases when utilising deep learning. Availability: The proposed a priori SNR estimator is available at: https://github.com/anicolson/DeepXi .

Subfields: Cognitive Neuroscience, Computational Mechanics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computational Mechanics

In Signal Processing

Citations in the corpus

Real Time Speech Enhancement in the Waveform Domain (2020, background): “Over the last years, there has been a growing interest towards DNN based methods for speech enhancement [34, 35, 36, 37, 20, 38, 39, 22, 40, 7, 41, 8, 42, 21, 37].”
DeepMMSE: A Deep Learning Approach to MMSE-Based Noise Power Spectral Density Estimation (2020, methodology): “In [25], the instantaneous a priori SNR (in dB), ξ dB [ l, k ] = 10 log 10 ( ξ l [ k ]) , was mapped to the interval [0 , 1] in order to improve the rate of convergence of the used stochastic gradient descent algorithm.”
Deep Residual-Dense Lattice Network for Speech Enhancement (2020, methodology): “The aforementioned RDL-Net conﬁgurations and the following network conﬁgurations were tasked with estimating the a priori SNR within the Deep Xi framework (Nicolson and Paliwal 2019).”