English

Efficient Knowledge Distillation for RNN-Transducer Models

Audio and Speech Processing 2020-11-13 v1 Sound

Abstract

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In this paper, we develop a distillation method for RNN-Transducer (RNN-T) models, a popular end-to-end neural network architecture for streaming speech recognition. Our proposed distillation loss is simple and efficient, and uses only the "y" and "blank" posterior probabilities from the RNN-T output probability lattice. We study the effectiveness of the proposed approach in improving the accuracy of sparse RNN-T models obtained by gradually pruning a larger uncompressed model, which also serves as the teacher during distillation. With distillation of 60% and 90% sparse multi-domain RNN-T models, we obtain WER reductions of 4.3% and 12.1% respectively, on a noisy FarField eval set. We also present results of experiments on LibriSpeech, where the introduction of the distillation loss yields a 4.8% relative WER reduction on the test-other dataset for a small Conformer model.

Keywords

Cite

@article{arxiv.2011.06110,
  title  = {Efficient Knowledge Distillation for RNN-Transducer Models},
  author = {Sankaran Panchapagesan and Daniel S. Park and Chung-Cheng Chiu and Yuan Shangguan and Qiao Liang and Alexander Gruenstein},
  journal= {arXiv preprint arXiv:2011.06110},
  year   = {2020}
}

Comments

5 pages, 1 figure, 2 tables; submitted to ICASSP 2021

R2 v1 2026-06-23T20:06:49.811Z