English

Discriminative Speech Recognition Rescoring with Pre-trained Language Models

Audio and Speech Processing 2023-10-11 v1

Abstract

Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis. Discriminative training, directly optimizing the minimum word-error-rate (MWER) criterion typically improves rescoring. In this study, we propose and explore several discriminative fine-tuning schemes for pre-trained LMs. We propose two architectures based on different pooling strategies of output embeddings and compare with probability based MWER. We conduct detailed comparisons between pre-trained causal and bidirectional LMs in discriminative settings. Experiments on LibriSpeech demonstrate that all MWER training schemes are beneficial, giving additional gains upto 8.5\% WER. Proposed pooling variants achieve lower latency while retaining most improvements. Finally, our study concludes that bidirectionality is better utilized with discriminative training.

Keywords

Cite

@article{arxiv.2310.06248,
  title  = {Discriminative Speech Recognition Rescoring with Pre-trained Language Models},
  author = {Prashanth Gurunath Shivakumar and Jari Kolehmainen and Yile Gu and Ankur Gandhe and Ariya Rastrow and Ivan Bulyko},
  journal= {arXiv preprint arXiv:2310.06248},
  year   = {2023}
}

Comments

ASRU 2023

R2 v1 2026-06-28T12:45:24.984Z