Metraipolis › archive › dc_facb80bfa5e4

From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition — arXiv:2610.41292

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41292
License (as archived): CC0-1.0
Archived: 2026-11-03T07:45:26.690Z
SHA-256 of the archived text: 57443dea5eb68fd81ac11eee26358fc826e10c9b9efa5cda0ddc1346a9b5fba9
Stable URL of this page: https://metraipolis.com/documento/dc_facb80bfa5e4

How to cite

From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition — arXiv:2610.41292 — arXiv (en), https://arxiv.org/abs/2610.41292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_facb80bfa5e4 (Metraipolis archive dc_facb80bfa5e4, sha256 57443dea5eb68fd81ac11eee26358fc826e10c9b9efa5cda0ddc1346a9b5fba9)

BibTeX

@misc{dcfacb80bfa5e4,
  title = {From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition — arXiv:2610.41292},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41292},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_facb80bfa5e4; sha256 57443dea5eb68fd81ac11eee26358fc826e10c9b9efa5cda0ddc1346a9b5fba9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Speech language models have expanded automatic speech recognition (ASR) from transcription to general speech-to-text generation. Yet existing benchmarks still assume a single ground-truth transcript per utterance, an assumption that struggles when models produce readable, formatted, or structured outputs. In this work, we introduce Grounded Generative Speech Recognition (GSR), reformulating speech recognition as generating semantically grounded text instead of a single transcript. We define a grounded reformulation space that characterizes all valid textual realizations supported by the input speech, and establish a four-level hierarchy of reformulation capabilities, including literal transcription, canonical reformulation, semantic reformulation and speech-grounded structuring. Based on this formulation, we present GSR-Bench, the first comprehensive benchmark designed to evaluate generative speech recognition systems beyond exact transcript matching. GSR-Bench covers diverse scenarios including refined meeting transcription, cross-dialect translation, context-aware speech understanding, and robustness under silent or noisy acoustic conditions. To address the limitations of word-level evaluation metrics, we develop a multi-dimensional evaluation framework combining speech grounding assessment and LLM-based semantic judgment, whose reliability is validated through human preference studies. Extensive experiments across representative architectures, ranging from conventional ASR systems to end-to-end Speech-LLMs, reveal fundamental trade-offs between transcription fidelity and generative reformulation ability. Our analysis further identifies critical failure modes, including acoustic hallucination, unsupported generation, and instruction drift, providing insights into the design and evaluation of future grounded generative speech systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.41292 — 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 2026-11-03T07:39:52.169Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).