RASA

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing2 results

Crowdsourced Text AggregationonCrowdSpeech test-other
Word Error Rate (WER)· 2021-07-02
15.67
best: 13.41 (ROVER)
SOTA
CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcription arXiv:2107.01091
Crowdsourced Text AggregationonCrowdSpeech test-clean
Word Error Rate (WER)· 2021-07-02
8.6
best: 7.29 (ROVER)
SOTA
CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcription arXiv:2107.01091