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.
@article{arxiv.2511.04035,
title = {WST: Weakly Supervised Transducer for Automatic Speech Recognition},
author = {Dongji Gao and Chenda Liao and Changliang Liu and Matthew Wiesner and Leibny Paola Garcia and Daniel Povey and Sanjeev Khudanpur and Jian Wu},
journal= {arXiv preprint arXiv:2511.04035},
year = {2025}
}