Facebook AI Research (FAIR) has published a research paper introducing Hidden Unit BERT (HuBERT), their latest approach for learning self-supervised speech representations. According to FAIR, self-supervised techniques for speech recognition are currently limited due to three factors: First, the presence of multiple sound units in each input utterance; secondly, the absence of lexicons of input sound units during the pre-training phase; and finally, the observation that sound units have variable lengths with no explicit segmentation.

Read more: https://analyticsindiamag.com/hubert-facebooks-latest-approach-to-self-supervised-speech-representation-learning/

#facebookai #artificial-intelligence