Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding

By Kai Zhen, Mi Suk Lee, Jongmo Sung, Seung-Wha Beack, Minje Kim. 2020

28 citations recorded by the source corpus.

Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the objective nature of the loss function usually leads to suboptimal sound quality as well as high run-time complexity due to the large model size. In this work, we present a psychoacoustic calibration scheme to re-define the loss functions of neural audio coding systems so that it can decode signals more perceptually similar to the reference, yet with a much lower model complexity. The proposed loss function incorporates the global masking threshold, allowing the reconstruction error that corresponds to inaudible artifacts. Experimental results show that the proposed model outperforms the baseline neural codec twice as large and consuming 23.4% more bits per second. With the proposed method, a lightweight neural codec, with only 0.9 million parameters, performs near-transparent audio coding comparable with the commercial MPEG-1 Audio Layer III codec at 112 kbps.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

1. Hyungseob Lim
2. Jihyun Lee
3. Hong-Goo Kang
4. Byeong Hyeon Kim
5. Inseon Jang

In Signal Processing

1. Hong-Goo Kang
2. Inseon Jang
3. Eunwoo Song
4. Ryuichi Yamamoto
5. Jae-Min Kim

Citations in the corpus

• Harp-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding (2021, unknown): “In [12], the idea of cascading multiple autoencoders [13] also show performance improvement, while the concatenation linearly increases model complexity.”
• End-to-End Neural Audio Coding in the MDCT Domain (2023, background): “The rNMR loss is similar to the noise modulation loss of [12] but is slightly different in that all the rectified error is averaged and that the loss is measured in terms of decibels (dB).”