DNN-Based Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement

by   Marvin Tammen, et al.

Multi-frame approaches for single-microphone speech enhancement, e.g., the multi-frame minimum-variance-distortionless-response (MVDR) filter, are able to exploit speech correlations across neighboring time frames. In contrast to single-frame approaches such as the Wiener gain, it has been shown that multi-frame approaches achieve a substantial noise reduction with hardly any speech distortion, provided that an accurate estimate of the correlation matrices and especially the speech interframe correlation vector is available. Typical estimation procedures of the correlation matrices and the speech interframe correlation (IFC) vector require an estimate of the speech presence probability (SPP) in each time-frequency bin. In this paper, we propose to use a bi-directional long short-term memory deep neural network (DNN) to estimate a speech mask and a noise mask for each time-frequency bin, using which two different SPP estimates are derived. Aiming at achieving a robust performance, the DNN is trained for various noise types and signal-to-noise ratios. Experimental results show that the multi-frame MVDR in combination with the proposed data-driven SPP estimator yields an increased speech quality compared to a state-of-the-art model-based estimator.



There are no comments yet.


page 4


Trainable Adaptive Window Switching for Speech Enhancement

This study proposes a trainable adaptive window switching (AWS) method a...

Acoustic echo suppression using a learning-based multi-frame minimum variance distortionless response filter

Distortion resulting from acoustic echo suppression (AES) is a common is...

Waveform to Single Sinusoid Regression to Estimate the F0 Contour from Noisy Speech Using Recurrent Deep Neural Networks

The fundamental frequency (F0) represents pitch in speech that determine...

Enhancement Of Coded Speech Using a Mask-Based Post-Filter

The quality of speech codecs deteriorates at low bitrates due to high qu...

Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement

Speech enhancement in the time-frequency domain is often performed by es...

Data-driven design of perfect reconstruction filterbank for DNN-based sound source enhancement

We propose a data-driven design method of perfect-reconstruction filterb...

Enhanced Factored Three-Way Restricted Boltzmann Machines for Speech Detection

In this letter, we propose enhanced factored three way restricted Boltzm...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.