Metraipolis › archive › dc_08e35af16617

StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution — arXiv:2609.03381

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03381
License (as archived)
CC0-1.0
Archived
2026-10-17T03:23:10.710Z
SHA-256 of the archived text
97a948c81d1dda3a00d1ccaf3bebf3bc22991a6a02aa233f11a3ff1c61d92c7c
Stable URL of this page
https://metraipolis.com/documento/dc_08e35af16617

How to cite

StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution — arXiv:2609.03381 — arXiv (en), https://arxiv.org/abs/2609.03381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08e35af16617 (Metraipolis archive dc_08e35af16617, sha256 97a948c81d1dda3a00d1ccaf3bebf3bc22991a6a02aa233f11a3ff1c61d92c7c)
BibTeX
@misc{dc08e35af16617,
  title = {StreamWSR: Streamable and Lightweight Waveform-Domain Neural Speech Super-Resolution — arXiv:2609.03381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08e35af16617; sha256 97a948c81d1dda3a00d1ccaf3bebf3bc22991a6a02aa233f11a3ff1c61d92c7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes StreamWSR, a Streamable neural Waveform-domain model for speech Super-Resolution (SR). By adopting a fully causal architecture with compact frame-level waveform representation, the proposed StreamWSR supports zero-look-ahead streaming inference while avoiding vocoder-based reconstruction and explicit phase prediction. Specifically, StreamWSR downsamples the input waveform into a compact frame-level representation using strided causal convolutions. Then, a lightweight causal long-short-term modeling backbone is employed to capture both local waveform structures and long-range historical dependencies under causal constraints. Finally, the modeled output is converted back to the waveform domain through a causal transposed-convolution and combined with the input waveform via a residual connection to generate the final high-resolution speech. Experimental results on 16 kHz speech SR show that StreamWSR achieves competitive or superior speech quality and intelligibility compared with representative waveform- and spectrum-based baselines, while maintaining a zero-look-ahead streaming advantage with only 9M parameters and 2G FLOPs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.03381 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T03:12:21.559Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).