Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SPECTRA

SPECTRA

Reported on 6 benchmarks across 4 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Sentiment AnalysisonMOSI
Accuracy· 2023-05-19
87.5
best: 90.35 (MMML)
SOTA
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579
Reading ComprehensiononMIntRec
Accuracy (20 classes)· 2023-05-19
73.48
best: 85.51 (Human)
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579
Sentiment AnalysisonCMU-MOSEI
Accuracy· 2023-05-19
87.34
best: 88.62 (SeMUL-PCD)
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579
Sentiment AnalysisonCMU-MOSI
Acc-2· uses extra data· 2023-05-19
87.5
best: 90.35 (MMML)
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579

Audio1 result

Emotion RecognitiononIEMOCAP
Accuracy· 2023-05-19
67.94
best: 73.95 (SDT)
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579

Miscellaneous1 result

Intent RecognitiononMIntRec
Accuracy (20 classes)· 2023-05-19
73.48
best: 85.51 (Human)
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment arXiv:2305.11579