Convolutional Neural Networks to Enhance Coded Speech

By Ziyue Zhao, Huijun Liu, Tim Fingscheidt. 2018

75 citations recorded by the source corpus.

Enhancing coded speech suffering from far-end acoustic background noise, quantization noise, and potentially transmission errors is a challenging task. In this paper, we propose two postprocessing approaches applying convolutional neural networks either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time-domain approach follows an end-to-end fashion, whereas the cepstral domain approach uses analysis–synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves perceptual evaluation of speech quality by up to 0.25 mean opinion score listening quality objective points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec. In a subjective comparison category rating listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to legacy G.711, even better than uncoded speech with statistical significance. The source code for the cepstral domain approach to enhance G.711-coded speech is made available.11https://github.com/ifnspaml/Enhancement-Coded-Speech.

Subfields: Biomedical Engineering, Cognitive Neuroscience, 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 Biomedical Engineering

1. Yu Tsao
2. Haici Yang
3. Wootaek Lim
4. Minje Kim
5. D. Jia
6. Arijit Biswas

In Cognitive Neuroscience

1. Yu Tsao
2. Haici Yang
3. Wootaek Lim
4. Szu-Wei Fu
5. Minje Kim
6. D. Jia
7. Arijit Biswas

In Signal Processing

1. Szu-Wei Fu
2. Minje Kim
3. Haici Yang
4. Wootaek Lim
5. Yu Tsao
6. Chien-Feng Liao
7. Shou-De Lin
8. D. Jia

Citations in the corpus

• Audio Codec Enhancement with Generative Adversarial Networks (2020, background): “[11], was the first to successfully demonstrate backwards compatible quality enhancement of narrow-”
• MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement (2019, background): “Some latest studies (Fu et al., 2018b; Koizumi et al., 2018; Zhang et al., 2018; Zhao et al., 2018a; Naithani et al., 2018; Kolbæk et al., 2018; Venkataramani et al., 2018; Venkataramani & Smaragdis, 2018; Zhao et al., 2018b) have focused on STOI score optimization to improve speech intelligibility.”
• Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding (2022, methodology): “To mitigate the issue, some efforts apply more complex models in the encoder to improve the quality of the features [9, 10] or use generative models for post-processing [11, 12, 13] at the end of the existing codec to facilitate signal restoration.”