English

Memory-Efficient Training of RNN-Transducer with Sampled Softmax

Audio and Speech Processing 2022-04-01 v1 Computation and Language

Abstract

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.

Keywords

Cite

@article{arxiv.2203.16868,
  title  = {Memory-Efficient Training of RNN-Transducer with Sampled Softmax},
  author = {Jaesong Lee and Lukas Lee and Shinji Watanabe},
  journal= {arXiv preprint arXiv:2203.16868},
  year   = {2022}
}

Comments

Submitted to INTERSPEECH 2022

R2 v1 2026-06-24T10:33:01.422Z