MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-clean
MT4SSL
#106
Word Error Rate (WER): 3.4
speech-recognition-on-librispeech-test-other
MT4SSL
#108
Word Error Rate (WER): 9.6
Rank counts only results with a code link.