ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

Chenyang Le, Yao Qian, Long Zhou, Shujie Liu 0001, Yanmin Qian, Michael Zeng 0001, Xuedong Huang 0001. ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

Authors

Chenyang Le

This author has not been identified. Look up 'Chenyang Le' in Google

Yao Qian

This author has not been identified. Look up 'Yao Qian' in Google

Long Zhou

This author has not been identified. Look up 'Long Zhou' in Google

Shujie Liu 0001

This author has not been identified. Look up 'Shujie Liu 0001' in Google

Yanmin Qian

This author has not been identified. Look up 'Yanmin Qian' in Google

Michael Zeng 0001

This author has not been identified. Look up 'Michael Zeng 0001' in Google

Xuedong Huang 0001

This author has not been identified. Look up 'Xuedong Huang 0001' in Google