ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets.
Jiatong ShiShih-Heng WangWilliam ChenMartijn BarteldsVanya Bannihatti KumarJinchuan TianXuankai ChangDan JurafskyKaren LivescuHung-yi LeeShinji WatanabePublished in: CoRR (2024)
Keyphrases
- multi lingual
- modeling framework
- maximum likelihood
- databases
- modeling method
- cross lingual
- expressive power
- speech recognition
- stochastic models
- models built
- database
- statistical models
- constraint satisfaction
- mathematical models
- complex systems
- language independent
- probabilistic model
- mathematical modeling
- english text
- language resources