BriefGPT.xyz
Sep, 2021
无监督预训练在语音识别中的性能与效率的折衷
Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition
HTML
PDF
Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q. Weinberger...
TL;DR
对预训练模型在自动语音识别中的性能和效率进行了研究，提出了一种新的模型架构SEW，其在不同训练环境下都取得了良好的性能和效率。
Abstract
This paper is a study of
performance-efficiency trade-offs
in
pre-trained models
for
automatic speech recognition
(ASR). We focus on
→