Metraipolis › archive › dc_6008b0949261

StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition — arXiv:2608.13717

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13717
License (as archived)
CC0-1.0
Archived
2026-10-19T02:27:50.846Z
SHA-256 of the archived text
0652f810668894c1159422a371a029ced8ccc04fc359faa9ca9185d8c213f84c
Stable URL of this page
https://metraipolis.com/documento/dc_6008b0949261

How to cite

StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition — arXiv:2608.13717 — arXiv (en), https://arxiv.org/abs/2608.13717 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6008b0949261 (Metraipolis archive dc_6008b0949261, sha256 0652f810668894c1159422a371a029ced8ccc04fc359faa9ca9185d8c213f84c)
BibTeX
@misc{dc6008b0949261,
  title = {StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition — arXiv:2608.13717},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13717},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6008b0949261; sha256 0652f810668894c1159422a371a029ced8ccc04fc359faa9ca9185d8c213f84c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13717. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlabeled audio is abundant. We present StreamHear, a semi-supervised pipeline that adapts a pretrained streaming student by fine-tuning an offline transducer teacher on the labeled training set, generating pseudo-labels on the unlabeled portion, and fine-tuning the student on the mixture. We further introduce a prior-regularized dynamic-programming realignment step that fixes chunk-level word placement using an ASR-hypothesis anchor. Across four datasets spanning financial calls, prepared read speech, and phone-quality dialogue, StreamHear consistently outperforms supervised student fine-tuning and narrows the gap to the offline teacher.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.13717 — 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 2026-10-19T02:20:31.897Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).