MIXTURE OF INFORMED EXPERTS FOR MULTILINGUAL SPEECH RECOGNITION

2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)(2021)

引用 27|浏览19
暂无评分
摘要
When trained on related or low-resource languages, multilingual speech recognition models often outperform their monolingual counterparts. However, these models can suffer from loss in performance for high resource or unrelated languages. We investigate the use of a mixture-of-experts approach to assign per-language parameters in the model to increase network capacity in a structured fashion. We introduce a novel variant of this approach, 'informed experts', which attempts to tackle inter-task conflicts by eliminating gradients from other tasks in these task-specific parameters. We conduct experiments on a real-world task with English, French and four dialects of Arabic to show the effectiveness of our approach. Our model matches or outperforms the monolingual models for almost all languages, with gains of as much as 31% relative. Our model also outperforms the baseline multilingual model for all languages by up to 9% relative.
更多
查看译文
关键词
end-to-end speech recognition, multilingual, RNN-T, language id, mixture of experts
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络