arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2210.08992cs.CLcs.SDeess.AS
收藏

序列到序列语音识别中与语言无关的语码转换

Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Carnegie Mellon University(卡内基梅隆大学)

Enes Yavuz Ugan, Christian Huber, Juan Hussain, Alexander Waibel

AI总结:

针对语码转换语音数据稀缺问题,提出拼接不同源语言音频及标签的数据增强方法,提升了E2E模型在CS语音和单语测试上的性能,未见句间语言切换WER降低5.03%。

摘要:

语码转换(CS)是指交替使用不同语言的单词和短语的现象。尽管当今的神经端到端(E2E)模型在自动语音识别(ASR)任务上取得了最先进的性能,但众所周知,这些系统非常依赖大量数据。然而,目前可用的转录和对齐的CS语音数据很少。为了克服这一问题并训练能够转录CS语音的多语言系统,我们提出了一种简单而有效的数据增强方法,即将不同源语言的音频及其对应标签进行拼接。通过使用这些训练数据,我们的E2E模型在转录CS语音方面有所提升,并且在单语测试中超越了单语模型。结果表明,这种增强技术甚至能将模型在训练期间未见过的句间语言切换上的性能提高5.03%的WER。

英文摘要:

Code-Switching (CS) is referred to the phenomenon of alternately using words and phrases from different languages. While today's neural end-to-end (E2E) models deliver state-of-the-art performances on the task of automatic speech recognition (ASR) it is commonly known that these systems are very data-intensive. However, there is only a few transcribed and aligned CS speech available. To overcome this problem and train multilingual systems which can transcribe CS speech, we propose a simple yet effective data augmentation in which audio and corresponding labels of different source languages are concatenated. By using this training data, our E2E model improves on transcribing CS speech. It also surpasses monolingual models on monolingual tests. The results show that this augmentation technique can even improve the model's performance on inter-sentential language switches not seen during training by 5,03% WER.

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。

↑