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

The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the time-frequency domain is proposed. A fully connected neural net...

Full description

Saved in:
Bibliographic Details
Main Authors: Korse, Srikanth, Gupta, Kishan, Fuchs, Guillaume
Format: Conference Proceeding
Language:English
Subjects:
Bit rate
Convolution
Convolutional codes
Deep Neural Network
Neural networks
Post-filtering
Speech coding
Speech Coding Enhancement
Speech enhancement
Time-frequency analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the time-frequency domain is proposed. A fully connected neural network (FCNN), a convolutional encoder-decoder (CED) network and a long short-term memory (LSTM) network are implemeted to estimate a real-valued mask per time-frequency bin. The proposed models were tested on the five lowest operating modes (6.65 kbps-15.85 kbps) of the Adaptive Multi-Rate Wideband codec (AMR-WB). Both objective and subjective evaluations confirm the enhancement of the coded speech and also show the superiority of the mask-based neural network system over a conventional heuristic post-filter used in the standard like ITU-T G.718.
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9053283