Tied \& Reduced RNN-T Decoder
(3 minutes introduction)
| Rami Botros (Google, USA), Tara N. Sainath (Google, USA), Robert David (Google, USA), Emmanuel Guzman (Google, USA), Wei Li (Google, USA), Yanzhang He (Google, USA) |
|---|
Previous works on the Recurrent Neural Network-Transducer (RNN-T) models have shown that, under some conditions, it is possible to simplify its prediction network with little or no loss in recognition accuracy [1, 2, 3]. This is done by limiting the context size of previous labels and/or using a simpler architecture for its layers instead of LSTMs. The benefits of such changes include reduction in model size, faster inference and power savings, which are all useful for on-device applications. In this work, we study ways to make the RNN-T decoder (prediction network + joint network) smaller and faster without degradation in recognition performance. Our prediction network performs a simple weighted averaging of the input embeddings, and shares its embedding matrix weights with the joint network’s output layer (a.k.a. weight tying, commonly used in language modeling [4]). This simple design, when used in conjunction with additional Edit-based Minimum Bayes Risk (EMBR) training, reduces the RNN-T Decoder from 23M parameters to just 2M, without affecting word-error rate (WER).
