Token2vec: A Joint Self-Supervised Pre-Training Framework Using Unpaired Speech and Text.

Xianghu Yue Junyi Ao Xiaoxue Gao Haizhou Li

Published in: ICASSP (2023)

Keyphrases

speech recognition
hearing impaired
training set
text mining
text retrieval
neural network
learning algorithm
training data
online learning
topic models
text documents
training process