Metraipolis › archive › dc_31ca5813df99
A Temporal-Envelope Frontend with Learnable Per-Channel Energy Normalization for Whisper-Based Children's ASR — arXiv:2609.26937
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26937
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:39:30.390Z
- SHA-256 of the archived text
3c0bdec838977dc2b064bc9eacbbe20e7b2eb581e3003428c7cd47c5b3b0c0f2- Stable URL of this page
https://metraipolis.com/documento/dc_31ca5813df99
How to cite
A Temporal-Envelope Frontend with Learnable Per-Channel Energy Normalization for Whisper-Based Children's ASR — arXiv:2609.26937 — arXiv (en), https://arxiv.org/abs/2609.26937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31ca5813df99 (Metraipolis archive dc_31ca5813df99, sha256 3c0bdec838977dc2b064bc9eacbbe20e7b2eb581e3003428c7cd47c5b3b0c0f2)
BibTeX
@misc{dc31ca5813df99,
title = {A Temporal-Envelope Frontend with Learnable Per-Channel Energy Normalization for Whisper-Based Children's ASR — arXiv:2609.26937},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26937},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31ca5813df99; sha256 3c0bdec838977dc2b064bc9eacbbe20e7b2eb581e3003428c7cd47c5b3b0c0f2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal envelopes carry cues critical to speech intelligibility, yet ASR frontends based on log-mel spectrograms do not explicitly model continuous sub-band envelope structure. This limitation is particularly acute for children's speech, where high acoustic variability demands robust feature representations. We propose a modular time-domain frontend that decomposes speech into sub-band envelopes using mel-spaced windowed-sinc filters and the Hilbert transform, with learnable per-channel energy normalization (PCEN) jointly optimized with the Whisper model. On the MyST children's speech corpus, systematic ablations identify full-band windowed-sinc filters, Hilbert envelopes, a 25 Hz smoothing cutoff, and learnable PCEN as the best configuration. Under the same Whisper-small fine-tuning setup, the frontend reduces WER from 13.16% to 11.08%, a 15.8% relative reduction over the log-mel baseline, and outperforms the evaluated Kid-Whisper checkpoint on the same cleaned test split. These results show that temporal-envelope representations and learnable frontend normalization are effective complements to backend adaptation for children's ASR. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.26937 — 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 2026-10-08T13:17:01.841Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).