Metraipolis › archive › dc_7cddd4964e6f

In-Context Adaptation of Encoder-Decoder Models in Speech Recognition — arXiv:2609.33865

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33865
License (as archived)
CC0-1.0
Archived
2026-10-07T21:53:11.086Z
SHA-256 of the archived text
b7bf56d5bfd88ceca768a1186be8112ba24ab28fe98c763b85b5c3839795c30d
Stable URL of this page
https://metraipolis.com/documento/dc_7cddd4964e6f

How to cite

In-Context Adaptation of Encoder-Decoder Models in Speech Recognition — arXiv:2609.33865 — arXiv (en), https://arxiv.org/abs/2609.33865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cddd4964e6f (Metraipolis archive dc_7cddd4964e6f, sha256 b7bf56d5bfd88ceca768a1186be8112ba24ab28fe98c763b85b5c3839795c30d)
BibTeX
@misc{dc7cddd4964e6f,
  title = {In-Context Adaptation of Encoder-Decoder Models in Speech Recognition — arXiv:2609.33865},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33865},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cddd4964e6f; sha256 b7bf56d5bfd88ceca768a1186be8112ba24ab28fe98c763b85b5c3839795c30d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In-context learning offers an appealing approach to adapt automatic speech recognition (ASR) models to new speakers, accents, and domains by providing speech-text pairs as demonstrations at inference time. Recent work shows that some LLM-based speech models are capable of ASR in-context adaptation, when providing interleaved speech-text demonstrations. In this work, we ask whether in-context adaptation is an inherent ability for all encoder-decoder models. We study two forms of demonstration, collated and interleaved demonstration, across six encoder-decoder models, spanning conventional cross-attention-based and LLM-based architectures. We find that all tested models are able to perform in-context adaptation out of the box, achieving up to 30% relative improvement in the oracle experiments and up to 23% using first-pass hypotheses. Through controlled experiments on three English datasets, we show that lexical and speaker information both contribute to successful adaptation. While interleaved demonstration is effective in certain cases, collated demonstration brings consistent adaptation across the board. Our results suggest that in-context adaptation for ASR is not unique to specific architectures, training, or demonstration approaches.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.33865 — 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 2026-10-07T21:27:08.558Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).