Pre-echo noise reduction in frequency-domain audio codecs

Lapierre, Jimmy; Lefebvre, Rémi

doi:10.1109/icassp.2017.7952243

Cited by 6 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Standardized speech codecs such as ITU-T Recommendation G.711 [7] and G.718 [8] have postfilters inside the decoder to reduce quantization noise and enhance low frequency pitch. There have also been approaches to reduce pre-echo with and without side [9]. In [10], envelope flattening was applied to high pass signals as a preprocessor to reduce pre-echo, and the gain for envelope flattening was transmitted to the receiver side as side information, which is used to reconstruct the signal during post-processing.…”

Section: Introductionmentioning

confidence: 99%

Enhancement of Coded Speech Using Neural Network-Based Side Information

et al. 2021

View full text Add to dashboard Cite

Audio codecs generate notable artifacts when operating at low bitrates, which degrade the quality of the coded audio significantly. There have been several approaches to enhance the quality of decoded signals with and without side information. While pre-or post-processing approaches without side information can be applied directly to existing systems without modifying codecs, approaches utilizing side information can further enhance the performance while maintaining backward-compatibility with existing codecs. In this paper, we propose a method to improve decoded signals using neural network-based side information. A neural network in the transmitter side that generates the side information and another neural network in the receiver side that estimates the log power spectra (LPS) of the original signal from the decoded signal and the side information are jointly trained to accurately reconstruct the original signal. In the same line with the analysis-by-synthesis, the neural network that generates the side information in the transmitter side takes not only the LPS of the original signal but also the LPS of the decoded signal as the input by decoding the encoded bitstream at the transmitter side. Experimental results show that the proposed audio codec enhancement scheme using neural network-based side information outperformed the audio codec enhancement without side information for the same codec operating at higher bitrates.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancement of Coded Speech Using Neural Network-Based Side Information

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The characteristics of coding artifacts depend on the codec and the employed coding tools, and the selected bitrate [2]. Classic codec enhancement methods [8], [9] are targeted at specific artifacts, they require very specialized knowledge about the codec and its' parameter settings, and hence are not easy to generalize. Furthermore, such backwards compatible enhancement methods do not provide significant audio quality improvement.…”

Section: Introductionmentioning

confidence: 99%

Audio Codec Enhancement with Generative Adversarial Networks

Biswas¹,

Jia²

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals as examples, we demonstrate a technique for restoring audio from coding noise based on generative adversarial networks (GAN). A primary advantage of the proposed GAN-based coded audio enhancer is that the method operates end-to-end directly on decoded audio samples, eliminating the need to design any manually-crafted frontend. Furthermore, the enhancement approach described in this paper can improve the sound quality of low-bit rate coded audio without any modifications to the existent standard-compliant encoders. Subjective tests illustrate that the proposed enhancer improves the quality of speech and difficult to code applause excerpts significantly.

show abstract