Average Jaccard Similarity on Clean Speech Utterances
86Avg Jaccard SimilarityBEST-STD 2.0
Evaluation results
| Method | Links | |
|---|---|---|
| BEST-STD 2.0Type=Speech Tokens, Tokens=10242025.12 | 86 | |
| Ours - TransformerType=Speech Tokens, Tokens=10242025.12 | 78 | |
| HuBERT-LargeType=ASR Posteriors, Tokens=322025.12 | 73 | |
| WavLM-LargeType=ASR Posteriors, Tokens=322025.12 | 72 | |
| BEST-STDType=Speech Tokens, Tokens=10242025.12 | 72 | |
| SpeechTokenizerType=Speech Tokens, Tokens=10242025.12 | 45 | |
| WavLM-LargeType=Speech Tokens, Tokens=10002025.12 | 40 |