MuCodec: Ultra Low-Bitrate Music Codec

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Yaoxun, Chen, Hangting, Yu, Jianwei, Tan, Wei, Gu, Rongzhi, Lei, Shun, Lin, Zhiwei, Wu, Zhiyong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912476647391232
author Xu, Yaoxun
Chen, Hangting
Yu, Jianwei
Tan, Wei
Gu, Rongzhi
Lei, Shun
Lin, Zhiwei
Wu, Zhiyong
author_facet Xu, Yaoxun
Chen, Hangting
Yu, Jianwei
Tan, Wei
Gu, Rongzhi
Lei, Shun
Lin, Zhiwei
Wu, Zhiyong
contents Music codecs are a vital aspect of audio codec research, and ultra low-bitrate compression holds significant importance for music transmission and generation. Due to the complexity of music backgrounds and the richness of vocals, solely relying on modeling semantic or acoustic information cannot effectively reconstruct music with both vocals and backgrounds. To address this issue, we propose MuCodec, specifically targeting music compression and reconstruction tasks at ultra low bitrates. MuCodec employs MuEncoder to extract both acoustic and semantic features, discretizes them with RVQ, and obtains Mel-VAE features via flow-matching. The music is then reconstructed using a pre-trained MEL-VAE decoder and HiFi-GAN. MuCodec can reconstruct high-fidelity music at ultra low (0.35kbps) or high bitrates (1.35kbps), achieving the best results to date in both subjective and objective metrics. Code and Demo: https://xuyaoxun.github.io/MuCodec_demo/.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13216
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MuCodec: Ultra Low-Bitrate Music Codec
Xu, Yaoxun
Chen, Hangting
Yu, Jianwei
Tan, Wei
Gu, Rongzhi
Lei, Shun
Lin, Zhiwei
Wu, Zhiyong
Sound
Audio and Speech Processing
Music codecs are a vital aspect of audio codec research, and ultra low-bitrate compression holds significant importance for music transmission and generation. Due to the complexity of music backgrounds and the richness of vocals, solely relying on modeling semantic or acoustic information cannot effectively reconstruct music with both vocals and backgrounds. To address this issue, we propose MuCodec, specifically targeting music compression and reconstruction tasks at ultra low bitrates. MuCodec employs MuEncoder to extract both acoustic and semantic features, discretizes them with RVQ, and obtains Mel-VAE features via flow-matching. The music is then reconstructed using a pre-trained MEL-VAE decoder and HiFi-GAN. MuCodec can reconstruct high-fidelity music at ultra low (0.35kbps) or high bitrates (1.35kbps), achieving the best results to date in both subjective and objective metrics. Code and Demo: https://xuyaoxun.github.io/MuCodec_demo/.
title MuCodec: Ultra Low-Bitrate Music Codec
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.13216