Slot Filling On Slurp
評価指標
F1
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | F1 | Paper Title | Repository |
|---|---|---|---|
| Partially Fine-tuned HuBERT | 0.753 | A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding | - |
| Multi-SLURP | 0.642 | SLURP: A Spoken Language Understanding Resource Package | |
| Finstreder (Conformer) | 0.395 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models | |
| TDT 0-6 | 0.8061 | Efficient Sequence Transduction by Jointly Predicting Tokens and Durations | |
| Finstreder (Quartznet) | 0.313 | Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models |
0 of 5 row(s) selected.