arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.14567eess.AScs.SD
收藏

基于标记级语言区分的语码转换语音识别语言混淆消除方法

Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization

Bytedance AI Lab(字节跳动人工智能实验室);Nanyang Technological University(南洋理工大学);Johns Hopkins University(约翰斯·霍普金斯大学)

Hexin Liu, Haihua Xu, Leibny Paola Garcia, Andy W. H. Khong, Yi He, Sanjeev Khudanpur

摘要:

语码转换(CS)是指在语音信号中语言发生转换并导致自动语音识别(ASR)语言混淆的现象。本文旨在从两个方面解决语言混淆问题,以提高CS-ASR:合并和解开语言信息。我们将语言信息的CS-ASR模型动态偏置模型与令牌级的语言后验是一个序列到序列的辅助语言日记模块的输出。相比之下,解纠缠过程通过对抗训练减少语言之间的差异,从而使两种语言规范化。我们在SEAME数据集上进行了实验。与基线模型相比,LD和语言后验偏差的联合优化都实现了性能的改善。所提出的方法的比较表明,结合语言信息是更有效的,比解开减少CS语音中的语言混乱。

英文摘要:

Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two perspectives: incorporating and disentangling language information. We incorporate language information in the CS-ASR model by dynamically biasing the model with token-level language posteriors which are outputs of a sequence-to-sequence auxiliary language diarization module. In contrast, the disentangling process reduces the difference between languages via adversarial training so as to normalize two languages. We conduct the experiments on the SEAME dataset. Compared to the baseline model, both the joint optimization with LD and the language posterior bias achieve performance improvement. The comparison of the proposed methods indicates that incorporating language information is more effective than disentangling for reducing language confusion in CS speech.

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。

↑