List your company
ResearchFormerly WizWand

Slot Filling on SLURP (test)

80.61F1 ScoreTDT 0-6
0.779621.504842.2362.9552Nov 4, 2021Jan 30, 2022Apr 28, 2022Jul 24, 2022Oct 20, 2022Jan 15, 2023Apr 13, 2023
Updated 8mo ago

Evaluation results

MethodLinks
TDT 0-6#params (M)=119, relative speedup=1.28x, max duration=62023.0480.61
TDT 0-4#params (M)=119, relative speedup=1.17x, max duration=42023.0480.03
TDT 0-8#params (M)=119, relative speedup=1.28x, max duration=82023.0479.9
TDT 0-2#params (M)=119, relative speedup=1.17x, max duration=22023.0479.43
RNNT#params (M)=119, relative speedup=-2023.0479.41
PF-hbt-largeFine-tuning strategy=Partial, Encoder Backbone=HuBERT, Model Size=Large2021.1178.92
EF-hbt-large-960hFine-tuning strategy=Entire, Encoder Backbone=HuBERT, Model Size=Large, Pre-training Corpus=960h2021.1178.89
EF-hbt-largeFine-tuning strategy=Entire, Encoder Backbone=HuBERT, Model Size=Large2021.1178.43
PF-hbt-large-960hFine-tuning strategy=Partial, Encoder Backbone=HuBERT, Model Size=Large, Pre-training Corpus=960h2021.1178.17
ESPnet-SLU#params (M)=109, relative speedup=N/A2023.0476.91
SpeechBrain#params (M)=96, relative speedup=N/A2023.0476.19
PF-hbt-baseFine-tuning strategy=Partial, Encoder Backbone=HuBERT, Model Size=Base2021.1175.32
EF-hbt-baseFine-tuning strategy=Entire, Encoder Backbone=HuBERT, Model Size=Base2021.1175.06
PF-w2v-baseFine-tuning strategy=Partial, Encoder Backbone=wav2vec 2.0, Model Size=Base2021.1174.73
CTI2021.1174.66
EF-w2v-base-960hFine-tuning strategy=Entire, Encoder Backbone=wav2vec 2.0, Model Size=Base, Pre-training Corpus=960h2021.1174.33
EF-w2v-baseFine-tuning strategy=Entire, Encoder Backbone=wav2vec 2.0, Model Size=Base2021.1174.32
PF-w2v-large-960hFine-tuning strategy=Partial, Encoder Backbone=wav2vec 2.0, Model Size=Large, Pre-training Corpus=960h2021.1174.03
PF-w2v-base-960hFine-tuning strategy=Partial, Encoder Backbone=wav2vec 2.0, Model Size=Base, Pre-training Corpus=960h2021.1173.78
EF-w2v-large-960hFine-tuning strategy=Entire, Encoder Backbone=wav2vec 2.0, Model Size=Large, Pre-training Corpus=960h2021.1173.39
PF-w2v-largeFine-tuning strategy=Partial, Encoder Backbone=wav2vec 2.0, Model Size=Large2021.1173.16
EF-w2v-largeFine-tuning strategy=Entire, Encoder Backbone=wav2vec 2.0, Model Size=Large2021.1172.45
Frozen-hbt-largeFine-tuning strategy=Frozen, Encoder Backbone=HuBERT, Model Size=Large2021.1160.07
Frozen-hbt-baseFine-tuning strategy=Frozen, Encoder Backbone=HuBERT, Model Size=Base2021.1157.06
Frozen-w2v-baseFine-tuning strategy=Frozen, Encoder Backbone=wav2vec 2.0, Model Size=Base2021.1137.66
Frozen-w2v-largeFine-tuning strategy=Frozen, Encoder Backbone=wav2vec 2.0, Model Size=Large2021.113.85