In automatic speech recognition (ASR) what a user says depends on the
particular context she is in. Typically, this context is represented as a set
of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E)
ASR sys- tem that utilizes such context. Our approach, which we re- fer to as
Contextual Listen, Attend and Spell (CLAS) jointly- optimizes the ASR
components along with embeddings of the context n-grams. During inference, the
CLAS system can be presented with context phrases which might contain out-of-
vocabulary (OOV) terms not seen during training. We com- pare our proposed
system to a more traditional contextualiza- tion approach, which performs
shallow-fusion between inde- pendently trained LAS and contextual n-gram models
during beam search. Across a number of tasks, we find that the pro- posed CLAS
system outperforms the baseline method by as much as 68% relative WER,
indicating the advantage of joint optimization over individually trained
components. Index Terms: speech recognition, sequence-to-sequence models,
listen attend and spell, LAS, attention, embedded speech recognition.

本文提出了一种新颖的自动语音识别 (CLAS) 系统，它对上下文短语进行深层次融合，对 ASR 进行了联合优化，并且在测试阶段可以识别未知词汇，相对于传统的浅层融合方法，提高了 68% 的相对识别率。