Zero-resource speech modeling on sWUGGY (in-vocabulary)
74.24Inter ScoreLAST
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LASTTWIST (Fine-tuning)=true, Adaptation layers=false, Model=OPT-350M, Codebook size=500, Backbone=HuBERT-base2024.09 | 74.24 | 58.37 | |
| k-meansTWIST (Fine-tuning)=true, Model=OPT-350M, Codebook size=500, Backbone=HuBERT-base2024.09 | 72.61 | 57.47 | |
| LASTTWIST (Fine-tuning)=false, Adaptation layers=true, Model=OPT-350M, Codebook size=500, Backbone=HuBERT-base2024.09 | 71.78 | 57.19 | |
| LASTTWIST (Fine-tuning)=false, Adaptation layers=false, Model=OPT-350M, Codebook size=500, Backbone=HuBERT-base2024.09 | 70.79 | 57.13 | |
| k-meansTWIST (Fine-tuning)=false, Model=OPT-350M, Codebook size=500, Backbone=HuBERT-base2024.09 | 63.53 | 54.06 |