ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912217896583168 |
|---|---|
| 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 | Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48~kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24~kbps bitrate as the baseline AuidoDec and ScoreDec. Objective and subjective evaluations demonstrate the out-of-domain robustness of ComplexDec trained using only the 30-hour VCTK corpus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling Wu, Yi-Chiao Marković, Dejan Krenn, Steven Gebru, Israel D. Richard, Alexander Audio and Speech Processing Sound Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48~kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24~kbps bitrate as the baseline AuidoDec and ScoreDec. Objective and subjective evaluations demonstrate the out-of-domain robustness of ComplexDec trained using only the 30-hour VCTK corpus. |
| title | ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2502.02019 |