Metraipolis › archive › dc_2d301b7eb2da
Wav2Aug: A Drop-In Speech Augmentation Policy — arXiv:2610.38656
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38656
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T03:01:08.911Z
- SHA-256 of the archived text
9365ebbf20ab530a1b0ac8f2eaae1d536258f6605133de333ba42fe36c980d9f- Stable URL of this page
https://metraipolis.com/documento/dc_2d301b7eb2da
How to cite
Wav2Aug: A Drop-In Speech Augmentation Policy — arXiv:2610.38656 — arXiv (en), https://arxiv.org/abs/2610.38656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d301b7eb2da (Metraipolis archive dc_2d301b7eb2da, sha256 9365ebbf20ab530a1b0ac8f2eaae1d536258f6605133de333ba42fe36c980d9f)
BibTeX
@misc{dc2d301b7eb2da,
title = {Wav2Aug: A Drop-In Speech Augmentation Policy — arXiv:2610.38656},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38656},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d301b7eb2da; sha256 9365ebbf20ab530a1b0ac8f2eaae1d536258f6605133de333ba42fe36c980d9f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
SpecAugment is the dominant speech augmentation policy, but researchers have studied it primarily for automatic speech recognition (ASR), and it operates on spectrograms, limiting its applicability to other speech tasks and waveform models. We propose Wav2Aug, a drop-in waveform augmentation policy that randomly samples two augmentations from a calibrated pool of waveform transformations. We calibrate the augmentation hyperparameters once and reuse them across tasks and architectures, eliminating task-specific tuning. Experiments on ten speech benchmarks show that Wav2Aug achieves ASR performance comparable to SpecAugment while improving over it on average across non-ASR tasks, yielding an average relative error reduction of 12.8% over the strongest compatible SpecAugment baseline. We further show that multi-view training provides additional gains, with two augmented views offering the best tradeoff between performance and computational cost. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.38656 — 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 2026-11-01T02:26:00.567Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).