Multi-Stream Self-Attention With Dilated 1D Convolutions

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

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

Audio2 results

Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· 2019-10-01
2.2
best: 0.985 (United Med ASR)
SOTA
State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions arXiv:1910.00716
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2019-10-01
5.8
best: 2.48 (SAMBA ASR)
State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions arXiv:1910.00716