Qi Luo

Low-rank adaptation of large language model rescoring for parameter-efficient speech recognition

Yu Yu, Huck Yang, Jari Kolehmainen, Prashanth Gurunath Shivakumar, Yi Gu, Sungho Ryu, Roger Ren, Qi Luo, Aditya Gourav, I-Fan Chen, Yi Chieh Liu, Tuan Dinh, Ankur Gandhe, Denis Filimonov, Shalini Ghosh, Andreas Stolcke, Ariya Rastrow, Ivan Bulyko

ASRU 2023

2023

We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high computational cost of scaling up the pretraining stage and adapting the pretrained models to specific domains limit their practical use in rescoring. Here we present

Conversational AI