BriefGPT.xyz
Apr, 2022
HuBERT-EE：高效语音识别的早期退出HuBERT模型
HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition
HTML
PDF
Ji Won Yoon, Beom Jun Woo, Nam Soo Kim
TL;DR
研究使用自监督模型HuBERT和wav2vec 2.0在自动语音识别中取得了显著的性能改进，但这些模型通常需要高昂的计算成本来实现出色的性能，从而拖慢了推理速度。为了提高模型效率，我们提出了一种早期退出方案，即HuBERT-EE，它允许模型动态地停止推理。
Abstract
Pre-training with
self-supervised models
, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in
automatic speech recognition
(ASR). However, these models usually require an ex
→