Michael Levit — accepted AI-conference papers

2025

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation

Sreyan Ghosh, Mohammad Sadegh Rasooli, Michael Levit, Peidong Wang, Jian Xue, Dinesh Manocha +1

ACL 2025finding

Generative Error Correction (GEC) has emerged as a powerful post-processing method to boost the performance of Automatic Speech Recognition (ASR) systems. In this paper, we first show that GEC models struggle to generalize beyond the specific types of errors encountered during training, limiting the…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2015

Token-level interpolation for class-based language models

Michael Levit, Andreas Stolcke, Shuangyu Chang, Sarangarajan Parthasarathy

ICASSP 2015accepted

We describe a method for interpolation of class-based n-gram language models. Our algorithm is an extension of the traditional EM-based approach that optimizes perplexity of the training set with respect to a collection of n-gram language models linearly combined in the probability space. However, u…

Cited by 0 Source ↗Scholar ↗