ScoreDec: A Phase-preserving High-Fidelity Audio Codec with A Generalized Score-based Diffusion Post-filter

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yi-Chiao, Marković, Dejan, Krenn, Steven, Gebru, Israel D., Richard, Alexander
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910304871383040
author Wu, Yi-Chiao
Marković, Dejan
Krenn, Steven
Gebru, Israel D.
Richard, Alexander
author_facet Wu, Yi-Chiao
Marković, Dejan
Krenn, Steven
Gebru, Israel D.
Richard, Alexander
contents Although recent mainstream waveform-domain end-to-end (E2E) neural audio codecs achieve impressive coded audio quality with a very low bitrate, the quality gap between the coded and natural audio is still significant. A generative adversarial network (GAN) training is usually required for these E2E neural codecs because of the difficulty of direct phase modeling. However, such adversarial learning hinders these codecs from preserving the original phase information. To achieve human-level naturalness with a reasonable bitrate, preserve the original phase, and get rid of the tricky and opaque GAN training, we develop a score-based diffusion post-filter (SPF) in the complex spectral domain and combine our previous AudioDec with the SPF to propose ScoreDec, which can be trained using only spectral and score-matching losses. Both the objective and subjective experimental results show that ScoreDec with a 24~kbps bitrate encodes and decodes full-band 48~kHz speech with human-level naturalness and well-preserved phase information.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12160
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ScoreDec: A Phase-preserving High-Fidelity Audio Codec with A Generalized Score-based Diffusion Post-filter
Wu, Yi-Chiao
Marković, Dejan
Krenn, Steven
Gebru, Israel D.
Richard, Alexander
Audio and Speech Processing
Although recent mainstream waveform-domain end-to-end (E2E) neural audio codecs achieve impressive coded audio quality with a very low bitrate, the quality gap between the coded and natural audio is still significant. A generative adversarial network (GAN) training is usually required for these E2E neural codecs because of the difficulty of direct phase modeling. However, such adversarial learning hinders these codecs from preserving the original phase information. To achieve human-level naturalness with a reasonable bitrate, preserve the original phase, and get rid of the tricky and opaque GAN training, we develop a score-based diffusion post-filter (SPF) in the complex spectral domain and combine our previous AudioDec with the SPF to propose ScoreDec, which can be trained using only spectral and score-matching losses. Both the objective and subjective experimental results show that ScoreDec with a 24~kbps bitrate encodes and decodes full-band 48~kHz speech with human-level naturalness and well-preserved phase information.
title ScoreDec: A Phase-preserving High-Fidelity Audio Codec with A Generalized Score-based Diffusion Post-filter
topic Audio and Speech Processing
url https://arxiv.org/abs/2401.12160