arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01380eess.AScs.AIcs.CLcs.LGcs.SD
收藏

用于领域自适应端到端语音识别的内部语言模型训练

Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition

Microsoft Corporation(微软公司)

Zhong Meng, Naoyuki Kanda, Yashesh Gaur, Sarangarajan Parthasarathy, Eric Sun, Liang Lu, Xie Chen, Jinyu Li, Yifan Gong

摘要:

使用内部语言模型估计(ILME)方法可以显著提高外部语言模型(LM)与现有端到端(E2 E)自动语音识别(ASR)系统集成的功效。在该方法中,在推断期间,从通过用外部LM分数内插E2 E分数获得的分数中减去内部LM分数。为了改进基于ILME的推理,我们提出了一种内部LM训练(ILMT)方法,通过仅更新影响内部LM估计的E2 E模型组件来最小化额外的内部LM损失。ILMT鼓励E2 E模型在其现有组件内形成独立的LM,而不会牺牲ASR的准确性。在ILMT之后,具有匹配的训练和推理标准的更加模块化的E2 E模型能够更彻底地消除源域内部LM,因此导致目标域外部LM的更有效的集成。使用30 K小时训练的递归神经网络传感器和基于注意力的编码器-解码器模型进行实验,ILMT与基于ILME的推理相比,在域外LibriSpeech和域内Microsoft生产测试集上,使用Shallow Fusion的标准E2 E训练分别实现了高达31.5%和11.4%的相对字错误率降低。

英文摘要:

The efficacy of external language model (LM) integration with existing end-to-end (E2E) automatic speech recognition (ASR) systems can be improved significantly using the internal language model estimation (ILME) method. In this method, the internal LM score is subtracted from the score obtained by interpolating the E2E score with the external LM score, during inference. To improve the ILME-based inference, we propose an internal LM training (ILMT) method to minimize an additional internal LM loss by updating only the E2E model components that affect the internal LM estimation. ILMT encourages the E2E model to form a standalone LM inside its existing components, without sacrificing ASR accuracy. After ILMT, the more modular E2E model with matched training and inference criteria enables a more thorough elimination of the source-domain internal LM, and therefore leads to a more effective integration of the target-domain external LM. Experimented with 30K-hour trained recurrent neural network transducer and attention-based encoder-decoder models, ILMT with ILME-based inference achieves up to 31.5% and 11.4% relative word error rate reductions from standard E2E training with Shallow Fusion on out-of-domain LibriSpeech and in-domain Microsoft production test sets, respectively.

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。

↑