RNN-Transducer has been one of promising architectures for end-to-end
automatic speech recognition. Although RNN-Transducer has many advantages
including its strong accuracy and streaming-friendly property, its high memory
consumption during training has been a critical problem for development. In
this work, we propose to apply sampled softmax to RNN-Transducer, which
requires only a small subset of vocabulary during training thus saves its
memory consumption. We further extend sampled softmax to optimize memory
consumption for a minibatch, and employ distributions of auxiliary CTC losses
for sampling vocabulary to improve model accuracy. We present experimental
results on LibriSpeech, AISHELL-1, and CSJ-APS, where sampled softmax greatly
reduces memory consumption and still maintains the accuracy of the baseline
model.

本文提出了使用采样 softmax 算法减少 RNN-Transducer 在训练过程中的内存消耗，并基于辅助 CTC losses 分布进行 sampling vocabulary 来提高模型准确性，在 LibriSpeech、AISHELL-1 和 CSJ-APS 三个数据集上进行实验，结果显示采样 softmax 显著降低了内存消耗，且仍然保持了基线模型的准确度。