Qing Li, Zhigang Deng, et al.
IEEE T-MI
In this paper, we propose a bilevel joint unsupervised and supervised training (BL-JUST) framework for automatic speech recognition. Compared to the conventional pretraining and fine-tuning strategy which is a disconnected twostage process, BL-JUST tries to optimize an acoustic model such that it simultaneously minimizes both the unsupervised and supervised loss functions. Because BL-JUST seeks matched local optima of both loss functions, acoustic representations learned by the acoustic model strike a good balance between being generic and task-specific. We solve the BL-JUST problem using penaltybased bilevel gradient descent and evaluate the trained deep neural network acoustic models on various datasets with a variety of architectures and loss functions. We show that BL-JUST can outperform the widely-used pre-training and fine-tuning strategy and some other popular semi-supervised techniques.
Qing Li, Zhigang Deng, et al.
IEEE T-MI
Nanda Kambhatla
ACL 2004
David A. Selby
IBM J. Res. Dev
Raghu Krishnapuram, Krishna Kummamuru
IFSA 2003