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.

翻译：RNN-T模型在自动语音识别中应用广泛，其依赖RNN-T损失函数实现输入音频与目标序列之间的长度对齐。然而，RNN-T损失函数的实现复杂度及其基于对齐的优化目标分别导致计算冗余和预测网络作用弱化。本文提出名为CIF-Transducer（CIF-T）的新型模型，该模型将连续积分-触发（CIF）机制与RNN-T模型相结合以实现高效对齐。通过这种方式，RNN-T损失函数被舍弃，从而降低计算量并让预测网络发挥更重要的作用。我们还引入Funnel-CIF、上下文模块、统一门控与双线性池化联合网络及辅助训练策略以进一步提升性能。在178小时AISHELL-1和10000小时WenetSpeech数据集上的实验表明，与RNN-T模型相比，CIF-T以更低计算开销取得了最先进的性能结果。