TQCodec: Towards neural audio codec for high-fidelity music streaming
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910037780201472 |
|---|---|
| author | He, Lixing Chen, Zhouxuan Liu, Mingshuai Sun, Xinran Wang, Wucheng Li, Minfu Kong, Lingcheng Zhao, Weifeng Zhou, Wenjiang |
| author_facet | He, Lixing Chen, Zhouxuan Liu, Mingshuai Sun, Xinran Wang, Wucheng Li, Minfu Kong, Lingcheng Zhao, Weifeng Zhou, Wenjiang |
| contents | We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from 32 kbps to 128 kbps, aligning with the standard quality of modern music streaming platforms. The model adopts an encoder-decoder architecture based on SEANet for efficient on-device computation and introduces several enhancements: an imbalanced network design for improved quality with low overhead, SimVQ for mid-frequency detail preservation, and a phase-aware waveform loss. Additionally, we introduce a perception-driven band-wise bit allocation strategy to prioritize perceptually critical lower frequencies. Evaluations on diverse music datasets demonstrate that TQCodec achieves superior audio quality at target bitrates, making it well-suited for high-quality audio applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01592 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TQCodec: Towards neural audio codec for high-fidelity music streaming He, Lixing Chen, Zhouxuan Liu, Mingshuai Sun, Xinran Wang, Wucheng Li, Minfu Kong, Lingcheng Zhao, Weifeng Zhou, Wenjiang Sound We propose TQCodec, a neural audio codec designed for high-bitrate, high-fidelity music streaming. Unlike existing neural codecs that primarily target ultra-low bitrates (<= 16kbps), TQCodec operates at 44.1 kHz and supports bitrates from 32 kbps to 128 kbps, aligning with the standard quality of modern music streaming platforms. The model adopts an encoder-decoder architecture based on SEANet for efficient on-device computation and introduces several enhancements: an imbalanced network design for improved quality with low overhead, SimVQ for mid-frequency detail preservation, and a phase-aware waveform loss. Additionally, we introduce a perception-driven band-wise bit allocation strategy to prioritize perceptually critical lower frequencies. Evaluations on diverse music datasets demonstrate that TQCodec achieves superior audio quality at target bitrates, making it well-suited for high-quality audio applications. |
| title | TQCodec: Towards neural audio codec for high-fidelity music streaming |
| topic | Sound |
| url | https://arxiv.org/abs/2603.01592 |