Tweeted By @ylecun
Self-Supervised Learning making strides in speech recognition.
— Yann LeCun (@ylecun) June 24, 2020
Wav2Vec 2.0 from FAIR uses a kind of contrastive SSL for pre-training.
This is the first time an SSL system reaches the very best results on a number of different ASR tasks.https://t.co/pqu1E320f4
1/N