arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11867cs.CLcs.SDeess.AS
收藏

用于端到端语音识别的神经FST类语言模型

Neural-FST Class Language Model for End-to-End Speech Recognition

Facebook(脸书)

Antoine Bruguier, Duc Le, Rohit Prabhavalkar, Dangna Li, Zhe Liu, Bo Wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer

摘要:

我们提出了神经FST类语言模型(NFCLM)的端到端的语音识别,一种新的方法,结合神经网络语言模型(NNLM)和有限状态转换器(FST)在一个数学上一致的框架。我们的方法利用了一个背景NNLM模型通用的背景文本与一个集合的特定领域的实体建模为个人FST。每个输出令牌由这些组件的混合生成;混合权重由单独训练的神经决策器估计。我们表明,NFCLM显着优于NNLM的15.8%,相对字出错率。NFCLM实现了与传统NNLM和FST浅融合相似的性能,同时不太容易发生过偏,并且紧凑12倍,使其更适合于设备上使用。

英文摘要:

We propose Neural-FST Class Language Model (NFCLM) for end-to-end speech recognition, a novel method that combines neural network language models (NNLMs) and finite state transducers (FSTs) in a mathematically consistent framework. Our method utilizes a background NNLM which models generic background text together with a collection of domain-specific entities modeled as individual FSTs. Each output token is generated by a mixture of these components; the mixture weights are estimated with a separately trained neural decider. We show that NFCLM significantly outperforms NNLM by 15.8% relative in terms of Word Error Rate. NFCLM achieves similar performance as traditional NNLM and FST shallow fusion while being less prone to overbiasing and 12 times more compact, making it more suitable for on-device usage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑