Simple and Effective Zero-shot Cross-lingual Phoneme Recognition

Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
复制标题

简单有效的零样本跨语言音素识别

DOI:
10.21437/interspeech.2022-60
复制
发表时间:
2021
期刊:
ArXiv
影响因子:
--
通讯作者:
Michael Auli
Michael Auli
中科院分区:
--
文献类型:
--
作者:
Qiantong Xu;Alexei Baevski;Michael Auli

文献摘要

参考文献

被引文献

相似文献

自训练、自监督预训练和无监督学习方面的最新进展使得无需任何标记数据即可实现性能良好的语音识别系统。然而,在许多情况下,这些方法并未利用相关语言的可用标记数据。本文通过微调多语言预训练的 wav2vec 2.0 模型来转录未见过的语言,扩展了之前关于零样本跨语言迁移学习的工作。这是通过使用发音特征将训练语言的音素映射到目标语言来完成的。实验表明,这种简单的方法明显优于先前引入特定于任务的架构并仅使用部分单语预训练模型的工作。
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related languages which is not utilized by these methods. This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages. This is done by mapping phonemes of the training languages to the target language using articulatory features. Experiments show that this simple method significantly outperforms prior work which introduced task-specific architectures and used only part of a monolingually pretrained model.
DOI: 10.1109/icassp40776.2020.9054362
发表时间: 2020-02
期刊: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
Xinjian Li;Siddharth Dalmia;Juncheng Billy Li;Matthew Russell Lee;Patrick Littell;Jiali Yao;Antonios Anastasopoulos;David R. Mortensen;Graham Neubig;A. Black;Florian Metze
通讯作者: Xinjian Li;Siddharth Dalmia;Juncheng Billy Li;Matthew Russell Lee;Patrick Littell;Jiali Yao;Antonios Anastasopoulos;David R. Mortensen;Graham Neubig;A. Black;Florian Metze