{"ID":2885964,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04814","arxiv_id":"2508.04814","title":"Pitch Accent Detection improves Pretrained Automatic Speech Recognition","abstract":"We show the performance of Automatic Speech Recognition (ASR) systems that use semi-supervised speech representations can be boosted by a complimentary pitch accent detection module, by introducing a joint ASR and pitch accent detection model. The pitch accent detection component of our model achieves a significant improvement on the state-of-the-art for the task, closing the gap in F1-score by 41%. Additionally, the ASR performance in joint training decreases WER by 28.3% on LibriSpeech, under limited resource fine-tuning. With these results, we show the importance of extending pretrained speech models to retain or re-learn important prosodic cues such as pitch accent.","short_abstract":"We show the performance of Automatic Speech Recognition (ASR) systems that use semi-supervised speech representations can be boosted by a complimentary pitch accent detection module, by introducing a joint ASR and pitch accent detection model. The pitch accent detection component of our model achieves a significant imp...","url_abs":"https://arxiv.org/abs/2508.04814","url_pdf":"https://arxiv.org/pdf/2508.04814v1","authors":"[\"David Sasu\",\"Natalie Schluter\"]","published":"2025-08-06T18:52:05Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}