CIF-T: A Novel Cif-based Transducer Architecture For Automatic Speech Recognition

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2023cif

Related papers

• Alignment Restricted Streaming Recurrent Neural Network Transducer (2020)11.19
• An Investigation Of Monotonic Transducers For Large-scale Automatic Speech Recognition (2022)6.77
• Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00
• Boundary And Context Aware Training For Cif-based Non-autoregressive End-to-end ASR (2021)7.81
• Residual Convolutional CTC Networks For Automatic Speech Recognition (2017)0.00
• Self-attention Transducers For End-to-end Speech Recognition (2019)11.93
• An Improved Single Step Non-autoregressive Transformer For Automatic Speech Recognition (2021)0.00
• A CTC Alignment-based Non-autoregressive Transformer For End-to-end Automatic Speech Recognition (2023)10.97