CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition
Zhang, Tian-Hao, Zhou, Dinghao, Zhong, Guiping, Zhou, Jiaming, Li, Baoxiang
–arXiv.org Artificial Intelligence
RNN-T models are widely used in ASR, which rely on the RNN-T loss to achieve length alignment between input audio and target sequence. However, the implementation complexity and the alignment-based optimization target of RNN-T loss lead to computational redundancy and a reduced role for predictor network, respectively. In this paper, we propose a novel model named CIF-Transducer (CIF-T) which incorporates the Continuous Integrate-and-Fire (CIF) mechanism with the RNN-T model to achieve efficient alignment. In this way, the RNN-T loss is abandoned, thus bringing a computational reduction and allowing the predictor network a more significant role. We also introduce Funnel-CIF, Context Blocks, Unified Gating and Bilinear Pooling joint network, and auxiliary training strategy to further improve performance. Experiments on the 178-hour AISHELL-1 and 10000-hour WenetSpeech datasets show that CIF-T achieves state-of-the-art results with lower computational overhead compared to RNN-T models.
arXiv.org Artificial Intelligence
Dec-14-2023
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Natural Language (1.00)
- Speech > Speech Recognition (1.00)
- Information Technology > Artificial Intelligence