{"slug": "from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech", "title": "From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition", "summary": "A team of researchers introduced Grounded Generative Speech Recognition (GSR), a reformulation of speech recognition as generating semantically grounded text rather than a single transcript, and released GSR-Bench, described as the first comprehensive benchmark for evaluating generative speech recognition beyond exact transcript matching. The work, posted as arXiv:2610.41292v1, defines a grounded reformulation space and a four-level hierarchy of capabilities — literal transcription, canonical reformulation, semantic reformulation and speech-grounded structuring — and covers scenarios including refined meeting transcription, cross-dialect translation, context-aware speech understanding, and robustness under silent or noisy acoustic conditions. Experiments across conventional ASR systems and end-to-end Speech-LLMs revealed trade-offs between transcription fidelity and generative reformulation ability, and identified failure modes including acoustic hallucination, unsupported generation and instruction drift.", "body_md": "arXiv:2610.41292v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech", "canonical_source": "https://arxiv.org/abs/2610.41292", "published_at": "2026-11-02 05:00:00+00:00", "updated_at": "2026-11-02 05:20:21.224734+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "ai-research", "large-language-models"], "entities": ["GSR-Bench", "Grounded Generative Speech Recognition", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech", "markdown": "https://wpnews.pro/news/from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech.md", "text": "https://wpnews.pro/news/from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech.txt", "jsonld": "https://wpnews.pro/news/from-transcription-to-reformulation-defining-and-benchmarking-grounded-speech.jsonld"}}