SpeechBERT

Reported on 3 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Speech2 results

DialogueonSpoken-SQuAD
F1 score· 2019-10-25
71.75
best: 77.1 (ALBERT)
SOTA
SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering arXiv:1910.11559
Spoken Language UnderstandingonSpoken-SQuAD
F1 score· 2019-10-25
71.75
best: 77.1 (ALBERT)
SOTA
SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering arXiv:1910.11559

Natural Language Processing1 result

Dialogue UnderstandingonSpoken-SQuAD
F1 score· 2019-10-25
71.75
best: 77.1 (ALBERT)
SOTA
SpeechBERT: An Audio-and-text Jointly Learned Language Model for End-to-end Spoken Question Answering arXiv:1910.11559