Gated Recurrent Unit Based Acoustic Modeling with Future Context
This work addresses the problem of low-latency future context modeling in acoustic models for speech recognition, offering an incremental improvement over existing methods.
The paper tackled the challenge of effectively modeling future context in RNN acoustic models while minimizing latency, proposing a model based on minimal gated recurrent unit (mGRU) with temporal encoding and convolution modules. It achieved better performance than LSTM and mGRU models on Switchboard and Mandarin ASR tasks, with a maximum latency of 170 ms and outperformed TDNN-LSTM with fewer parameters.
The use of future contextual information is typically shown to be helpful for acoustic modeling. However, for the recurrent neural network (RNN), it's not so easy to model the future temporal context effectively, meanwhile keep lower model latency. In this paper, we attempt to design a RNN acoustic model that being capable of utilizing the future context effectively and directly, with the model latency and computation cost as low as possible. The proposed model is based on the minimal gated recurrent unit (mGRU) with an input projection layer inserted in it. Two context modules, temporal encoding and temporal convolution, are specifically designed for this architecture to model the future context. Experimental results on the Switchboard task and an internal Mandarin ASR task show that, the proposed model performs much better than long short-term memory (LSTM) and mGRU models, whereas enables online decoding with a maximum latency of 170 ms. This model even outperforms a very strong baseline, TDNN-LSTM, with smaller model latency and almost half less parameters.