2020年6月3日 (三) 00:46的版本

Introduction

The Multilingual Minorlingual Automatic Speech Recognition (M2ASR) project is a state key project supported by the national natural science foundation of China (NSFC). It is a three-party collaboration, including Tsinghua University, Northwest Minzu University, and Xinjiang University. The aim of this project is to construct speech recognition systems for five minor languages in China (Tibetan, Mongolia, Uyghur, Kazak and Kirgiz). However, our ambition is beyond that scope: we hope to construct a full set of linguistic and speech resources and tools for the 5 languages, and make them open and free for research purposes. We call this the M2ASR Free Data Program.

• This project is led by Prof. Thomas Fang Zheng, and the research leader is Prof. Dong Wang.

• The logo of the project was designed by Dr. Zhiyuan Tang and Dr. Dong Wang.

News

• We will have a special session on APSIPA ASC 2018.

• Topic: Multilingual speech and language processing for minority languages
• Organizer: Dong Wang, Guanyu Li, Mijit Ablimit

• We have organized a special session on APSIPA ASC 2017.

• Topic: Multilingual speech and language processing for minority languages
• Organizer: Dong Wang, Guanyu Li, Mijit Ablimit
• link

• The project team has organized APSIPA ASC 2019 in Lanzhou, China.

• link

Main people

Tsinghua University

• Thomas Fang Zheng, Project Leader [homepage]
• Dong Wang, Project Research Leader [homepage]
• Zhiyuan Tang [homepage]
• Lantian Li [homepage]
• Ying Shi [homepage]

Northwest Minzu University

• Hongzhi Yu
• Guanyu Li
• Shipeng Xu

Xinjiang University

• Askar Hamdulla
• Mijit Ablimit

Achievement

• Documents
• Delivery
• Publications
• Data Resource

Footprint

• Weekly report

• Milestone report

• Paper sharing

• Code sharing