An open speech resource for Tibetan multi-dialect and multitask recognition. (8th May 2020)

• Record Type: Journal Article
• Authors: Zhao, Yue; Xu, Xiaona; Yue, Jianjian; Song, Wei; Li, Xiali; Wu, Licheng; Ji, Qiang
• Is Part Of: International journal of computational science and engineering. Volume 22:Number 2/3(2020)
• Page Start: 297
• Page End: 304
• Publication Date: 2020-05-08
• Subjects: Tibetan language -- multi-dialect speech recognition -- multitask learning -- speech corpus; Computer science -- Mathematics -- Periodicals; Computer simulation -- Mathematical aspects -- Periodicals; Computational intelligence -- Periodicals; 004.015105
• Languages: English
• ISSNs: 1742-7185

Abstract

This paper introduces a Tibetan multi-dialect data resource for multitask speech research. It can be used for Tibetan multi-dialect speech recognition, Tibetan speaker recognition, Tibetan dialect identification, and Tibetan speech synthesis. The resource consists of 30 hours Lhasa-Ü-Tsang dialect; 8.7 hours Kham dialect, including 3.4 hours Yushu dialect, 3.3 hours Dege dialect and 2 hours Changdu dialect; 10 hours Amdo pastoral dialect. Other resources are also provided for Lhasa-Ü-Tsang dialect including phoneme set, pronunciation dictionary and the codes for constructing the Lhasa-Ü-Tsang speech recognition baseline system. Meanwhile, for Tibetan multi-dialect and multitask speech recognition, the codes and recognition results based on WaveNet-connectionist temporal classification (WaveNet-CTC) are provided. All the resources are free for researchers and publicly available, which effectively compensates for the shortage of public Tibetan multi-dialect speech resources in order to promote the development of Tibetan multi-dialect speech processing technology.