Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Nobuyasu Itoh, George Saon
Abstract
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, near state-of-the-art ASR systems remains unexplored. In this study, we incorporate LLM rescoring into one of the most competitive ASR baselines: the Conformer-Transducer model. We demonstrate that consistent improvement is achieved by the LLM's bidirectionality, pretraining, in-domain finetuning and context augmentation. Furthermore, our lexical analysis sheds light on how each of these components may be contributing to the ASR performance.
Create a lesson
Related papers
Mechanistic Interpretability Needs a Logic of Inference
Zhimin Hu, Chen Jiang, Hanbo Xie et al.
Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
Evelyn Y. Garland, Carola F. Berger
When does text encoding matter for language modeling?
Eugene Jang, Catherine Arnett, Terra Blevins
Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models
Amir Mann, Jonathan Fhima, Shaked Brody et al.
ARE-bench: Benchmarking Agents' Research Ability in Real-World Researcher Sessions and Workspaces
Jiahang Lin, Wanying Ren, Wanghan Xu et al.
Point-in-Time Encoders for Earnings Calls
Alessio Brini