Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition

19 May 2020  ·  Yan Gao, Titouan Parcollet, Nicholas Lane ·

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from ensembles of acoustic models has recently shown promising results in increasing recognition performance. In this paper, we propose an extension of multi-teacher distillation methods to joint CTC-attention end-to-end ASR systems. We also introduce three novel distillation strategies. The core intuition behind them is to integrate the error rate metric to the teacher selection rather than solely focusing on the observed losses. In this way, we directly distill and optimize the student toward the relevant metric for speech recognition. We evaluate these strategies under a selection of training procedures on different datasets (TIMIT, Librispeech, Common Voice) and various languages (English, French, Italian). In particular, state-of-the-art error rates are reported on the Common Voice French, Italian and TIMIT datasets.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here