English

Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition

Computation and Language 2024-12-12 v1

Abstract

In this paper, we propose a bilevel joint unsupervised and supervised training (BL-JUST) framework for automatic speech recognition. Compared to the conventional pre-training and fine-tuning strategy which is a disconnected two-stage 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 penalty-based 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.

Keywords

Cite

@article{arxiv.2412.08548,
  title  = {Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition},
  author = {Xiaodong Cui and A F M Saif and Songtao Lu and Lisha Chen and Tianyi Chen and Brian Kingsbury and George Saon},
  journal= {arXiv preprint arXiv:2412.08548},
  year   = {2024}
}

Comments

Accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing

R2 v1 2026-06-28T20:31:14.770Z