arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.04062cs.CLcs.SDeess.AS
收藏

基于CTC的ASR与电话条件掩蔽LM的非自回归纠错

Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM

Graduate School of Informatics, Kyoto University(京都大学信息学研究生院)

Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

摘要:

基于连接主义时态分类(CTC)的模型由于其非自回归特性而在自动语音识别(ASR)中受到广泛关注。为了充分利用纯文本数据,语言模型(LM)集成方法,如重评分和浅层融合已被广泛用于CTC。然而,由于需要束搜索,它们失去了CTC的非自回归性质,这降低了推理速度。在这项研究中,我们提出了一个错误纠正方法与音素条件掩蔽LM(PC-MLM)。在所提出的方法中,不太自信的词令牌在一个贪婪的解码输出CTC被掩盖。PC-MLM然后预测这些屏蔽词令牌给出未屏蔽的单词和电话从CTC预测。我们进一步将其扩展到可删除的PC-MLM,以解决插入错误。由于CTC和PC-MLM都是非自回归模型,因此该方法能够实现快速LM积分。在领域自适应环境下对自然日语语料库(CSJ)和TED-LIUM 2进行的实验结果表明,该方法在推理速度和识别准确率方面均优于再评分和浅层融合。

英文摘要:

Connectionist temporal classification (CTC) -based models are attractive in automatic speech recognition (ASR) because of their non-autoregressive nature. To take advantage of text-only data, language model (LM) integration approaches such as rescoring and shallow fusion have been widely used for CTC. However, they lose CTC's non-autoregressive nature because of the need for beam search, which slows down the inference speed. In this study, we propose an error correction method with phone-conditioned masked LM (PC-MLM). In the proposed method, less confident word tokens in a greedy decoded output from CTC are masked. PC-MLM then predicts these masked word tokens given unmasked words and phones supplementally predicted from CTC. We further extend it to Deletable PC-MLM in order to address insertion errors. Since both CTC and PC-MLM are non-autoregressive models, the method enables fast LM integration. Experimental evaluations on the Corpus of Spontaneous Japanese (CSJ) and TED-LIUM2 in domain adaptation setting shows that our proposed method outperformed rescoring and shallow fusion in terms of inference speed, and also in terms of recognition accuracy on CSJ.

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。

↑