{"ID":2845167,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.04035","arxiv_id":"2511.04035","title":"WST: Weakly Supervised Transducer for Automatic Speech Recognition","abstract":"The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain. To mitigate this reliance, we propose a Weakly Supervised Transducer (WST), which integrates a flexible training graph designed to robustly handle errors in the transcripts without requiring additional confidence estimation or auxiliary pre-trained models. Empirical evaluations on synthetic and industrial datasets reveal that WST effectively maintains performance even with transcription error rates of up to 70%, consistently outperforming existing Connectionist Temporal Classification (CTC)-based weakly supervised approaches, such as Bypass Temporal Classification (BTC) and Omni-Temporal Classification (OTC). These results demonstrate the practical utility and robustness of WST in realistic ASR settings. The implementation will be publicly available.","short_abstract":"The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain. To mitigate this reliance, we propose a Weakly Supervised Transducer (WST), whic...","url_abs":"https://arxiv.org/abs/2511.04035","url_pdf":"https://arxiv.org/pdf/2511.04035v1","authors":"[\"Dongji Gao\",\"Chenda Liao\",\"Changliang Liu\",\"Matthew Wiesner\",\"Leibny Paola Garcia\",\"Daniel Povey\",\"Sanjeev Khudanpur\",\"Jian Wu\"]","published":"2025-11-06T04:14:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}