arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.05129eess.AScs.CLcs.SD
收藏

基于神经文本生成的数据增强在形态丰富语音识别中的有效性研究

On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech

Budapest University of Technology and Economics(布达佩斯技术与经济大学);SpeechTex Ltd.(SpeechTex有限公司);THINKTech Research Center(THINKTech研究中心)

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

摘要:

近年来,先进的神经网络模型已经渗透到自动语音识别(ASR)中,然而在语言建模中,许多系统仍然部分或全部依赖于传统的Back-off N-gram语言模型(BNLM)。其原因是训练和使用神经语言模型的高成本和复杂性,主要是通过添加第二次解码(重新评分)来实现。在我们最近的工作中,我们通过将知识从递归神经网络语言模型(RNNLM)转移到具有基于文本生成的数据增强的单通道BNLM,显着提高了会话语音转录系统的在线性能。在本文中,我们分析了可转移知识的数量,并证明了神经增强LM(RNN-BNLM)可以通过丢弃第二次解码并使系统具有实时能力来帮助捕获RNNLM的近50%的知识。我们还系统地比较了词和子词LM,并表明基于子词的神经文本增强在资源不足的情况下特别有益。此外,我们还表明,在第一遍使用RNN-BNLM,然后是神经第二遍,离线ASR结果甚至可以显着改善。

英文摘要:

Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason for this are the high cost and complexity of training and using neural language models, mostly possible by adding a second decoding pass (rescoring). In our recent work we have significantly improved the online performance of a conversational speech transcription system by transferring knowledge from a Recurrent Neural Network Language Model (RNNLM) to the single pass BNLM with text generation based data augmentation. In the present paper we analyze the amount of transferable knowledge and demonstrate that the neural augmented LM (RNN-BNLM) can help to capture almost 50% of the knowledge of the RNNLM yet by dropping the second decoding pass and making the system real-time capable. We also systematically compare word and subword LMs and show that subword-based neural text augmentation can be especially beneficial in under-resourced conditions. In addition, we show that using the RNN-BNLM in the first pass followed by a neural second pass, offline ASR results can be even significantly improved.

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。

↑