Metraipolis › archive › dc_3aaa0af5dcef

BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio — arXiv:2609.31165

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31165
License (as archived)
CC0-1.0
Archived
2026-10-08T02:19:17.750Z
SHA-256 of the archived text
74df55c13bb33e6062c1724bd20b912ec03dc551d27085a5bdd090d0fe6e5d14
Stable URL of this page
https://metraipolis.com/documento/dc_3aaa0af5dcef

How to cite

BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio — arXiv:2609.31165 — arXiv (en), https://arxiv.org/abs/2609.31165 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3aaa0af5dcef (Metraipolis archive dc_3aaa0af5dcef, sha256 74df55c13bb33e6062c1724bd20b912ec03dc551d27085a5bdd090d0fe6e5d14)
BibTeX
@misc{dc3aaa0af5dcef,
  title = {BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio — arXiv:2609.31165},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31165},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3aaa0af5dcef; sha256 74df55c13bb33e6062c1724bd20b912ec03dc551d27085a5bdd090d0fe6e5d14},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31165. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech-breath segmentation is a fundamental preprocessing step in respiratory audio analysis, enabling applications such as respiratory acoustic biomarker extraction, lung function prediction and disease monitoring. Existing approaches, including threshold methods, Fourier Transform-based techniques, and unsupervised and pretrained voice activity detection (VAD) models, primarily focus on speech detection and often classify breathing events as non-speech or silence, limiting their applicability for precise breath detection. To address this limitation, we propose BreathGRU, a semi-supervised Bidirectional Gated Recurrent Unit (BiGRU) framework specifically designed for speech-breath segmentation. The proposed framework combines frame-level acoustic feature extraction with bidirectional recurrent modelling, pseudo-label refinement and duration-constrained Segmental Viterbi decoding to produce speech and breath segmentation. BreathGRU was evaluated against the existing approaches, using manually annotated recordings. Performance was assessed using event-based, time-based, overlap-based, duration-based and boundary-based segmentation metrics. Experiment results demonstrated that BreathGRU achieved the highest breath event recall (0.83), the lowest onset-localisation error (0.14s) and the highest Mean Match Intersection over Union (0.81), with competitive overall segmentation performance compared to large pretrained VAD models like Silero. Qualitative evaluation on manually annotated recordings further showed close agreement between BreathGRU and manual annotation, with better breath detection compared to Silero. These findings demonstrate that explicit breath event modelling provides advantages over general-purpose VAD models and establish BreathGRU as an effective speech-breath segmentation framework which can be applied for respiratory audio analysis and pulmonary healthcare applications.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.31165 — 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 2026-10-08T01:43:06.810Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).