Metraipolis › archive › dc_2a42b97ffccc

Pretrained ASR Pseudo-labeling for Noisy Police Audio — arXiv:2609.30469

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.30469
License (as archived): CC0-1.0
Archived: 2026-10-08T01:38:09.886Z
SHA-256 of the archived text: d87633e135ba7ad690948b1e5a05dcf6c44cf551a1bd25de6b3f902bf2c38631
Stable URL of this page: https://metraipolis.com/documento/dc_2a42b97ffccc

How to cite

Pretrained ASR Pseudo-labeling for Noisy Police Audio — arXiv:2609.30469 — arXiv (en), https://arxiv.org/abs/2609.30469 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a42b97ffccc (Metraipolis archive dc_2a42b97ffccc, sha256 d87633e135ba7ad690948b1e5a05dcf6c44cf551a1bd25de6b3f902bf2c38631)

BibTeX

@misc{dc2a42b97ffccc,
  title = {Pretrained ASR Pseudo-labeling for Noisy Police Audio — arXiv:2609.30469},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30469},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a42b97ffccc; sha256 d87633e135ba7ad690948b1e5a05dcf6c44cf551a1bd25de6b3f902bf2c38631},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30469. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pretrained ASR systems perform poorly on noisy Broadcast Police Communication (BPC), hindering efforts to understand police decision-making. Pseudo-labeling offers an unsupervised path to improve ASR without expensive human labels, but the efficacy of this approach on very noisy domains is not known. In this work, we systematically assess the opportunities and limits of pseudo-labeling to adapt foundation ASR models (Whisper and Qwen3-ASR) to noisy BPC domain corpora from Baltimore and Chicago. We demonstrate that existing internal confidence metrics (log-probabilities and STAR scores) fail to distinguish between high and low quality BPC pseudo-labels, and we introduce an external LLM-as-a-judge filtering paradigm that leverages parametric knowledge to discard contextually implausible transcripts. Our LLM-judging filters more aggressively than internal metrics and significantly reduces WER of the pseudo-labeled training sets across the Baltimore and Chicago BPC corpora, though a substantial gap remains relative to an oracle filter. We also introduce a new cross-model pseudo-labeling paradigm where one model is finetuned with pseudo-labels from the other, and we identify this method as a promising direction for future pseudo-labeling work.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30469 — 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 2026-10-08T01:12:14.240Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).