BriefGPT.xyz
Apr, 2019
谁需要词汇？无词汇语音识别
Who Needs Words? Lexicon-Free Speech Recognition
HTML
PDF
Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
TL;DR
本文研究了基于字符的语言模型在无需限制解码字典情况下，进行语音识别表现与基于单词的模型相当，尤其通过利用卷积模型对大（字符）背景的有效使用，在处理具有OOV单词的语音识别中，lexicon-free字符模型的表现优于基于字符或单词LM的字典识别。
Abstract
lexicon-free
speech recognition
naturally deals with the problem of out-of-vocabulary (OOV) words. In this paper, we show that
character-based
→