MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xiao-Hang, Ai, Yang, Zheng, Rui-Chen, Du, Hui-Peng, Lu, Ye-Xin, Ling, Zhen-Hua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929571865034752
author Jiang, Xiao-Hang
Ai, Yang
Zheng, Rui-Chen
Du, Hui-Peng
Lu, Ye-Xin
Ling, Zhen-Hua
author_facet Jiang, Xiao-Hang
Ai, Yang
Zheng, Rui-Chen
Du, Hui-Peng
Lu, Ye-Xin
Ling, Zhen-Hua
contents In this paper, we propose MDCTCodec, an efficient lightweight end-to-end neural audio codec based on the modified discrete cosine transform (MDCT). The encoder takes the MDCT spectrum of audio as input, encoding it into a continuous latent code which is then discretized by a residual vector quantizer (RVQ). Subsequently, the decoder decodes the MDCT spectrum from the quantized latent code and reconstructs audio via inverse MDCT. During the training phase, a novel multi-resolution MDCT-based discriminator (MR-MDCTD) is adopted to discriminate the natural or decoded MDCT spectrum for adversarial training. Experimental results confirm that, in scenarios with high sampling rates and low bitrates, the MDCTCodec exhibited high decoded audio quality, improved training and generation efficiency, and compact model size compared to baseline codecs. Specifically, the MDCTCodec achieved a ViSQOL score of 4.18 at a sampling rate of 48 kHz and a bitrate of 6 kbps on the public VCTK corpus.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00464
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
Jiang, Xiao-Hang
Ai, Yang
Zheng, Rui-Chen
Du, Hui-Peng
Lu, Ye-Xin
Ling, Zhen-Hua
Sound
Audio and Speech Processing
In this paper, we propose MDCTCodec, an efficient lightweight end-to-end neural audio codec based on the modified discrete cosine transform (MDCT). The encoder takes the MDCT spectrum of audio as input, encoding it into a continuous latent code which is then discretized by a residual vector quantizer (RVQ). Subsequently, the decoder decodes the MDCT spectrum from the quantized latent code and reconstructs audio via inverse MDCT. During the training phase, a novel multi-resolution MDCT-based discriminator (MR-MDCTD) is adopted to discriminate the natural or decoded MDCT spectrum for adversarial training. Experimental results confirm that, in scenarios with high sampling rates and low bitrates, the MDCTCodec exhibited high decoded audio quality, improved training and generation efficiency, and compact model size compared to baseline codecs. Specifically, the MDCTCodec achieved a ViSQOL score of 4.18 at a sampling rate of 48 kHz and a bitrate of 6 kbps on the public VCTK corpus.
title MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2411.00464