Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing.
Yonggan FuYang ZhangKaizhi QianZhifan YeZhongzhi YuCheng-I LaiYingyan LinPublished in: CoRR (2022)
Keyphrases
- speech processing
- speech recognition
- multi task
- signal processing
- speaker identification
- natural language processing
- multimedia systems
- artificial intelligence
- variable length
- english text
- digital libraries
- language independent
- multitask learning
- bayesian networks
- e learning
- gaussian mixture model
- text to speech
- computer vision