{"ID":2871749,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10116","arxiv_id":"2509.10116","title":"Prominence-aware automatic speech recognition for conversational speech","abstract":"This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-tuning wav2vec2 models to classify word-level prominence. The detector was then used to automatically annotate prosodic prominence in a large corpus. Based on those annotations, we trained novel prominence-aware ASR systems that simultaneously transcribe words and their prominence levels. The integration of prominence information did not change performance compared to our baseline ASR system, while reaching a prominence detection accuracy of 85.53% for utterances where the recognized word sequence was correct. This paper shows that transformer-based models can effectively encode prosodic information and represents a novel contribution to prosody-enhanced ASR, with potential applications for linguistic research and prosody-informed dialogue systems.","short_abstract":"This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-tuning wav2vec2 models to classify word-level prominence. The detector was then used to automaticall...","url_abs":"https://arxiv.org/abs/2509.10116","url_pdf":"https://arxiv.org/pdf/2509.10116v1","authors":"[\"Julian Linke\",\"Barbara Schuppler\"]","published":"2025-09-12T10:18:38Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"eess.AS\"]","methods":"[\"Transformer\"]","has_code":false}