Recognizing specific key phrases is an essential task for contextualized Automatic Speech Recognition (ASR). However, most existing context-biasing approaches have limitations associated with the necessity of additional model training, significantly slow down the decoding process, or constrain the choice of the ASR system type. This paper proposes a universal ASR context-biasing framework that supports all major types: CTC, Transducers, and Attention Encoder-Decoder models. The framework is based on a GPU-accelerated word boosting tree, which enables it to be used in shallow fusion mode for greedy and beam search decoding without noticeable speed degradation, even with a vast number of key phrases (up to 20K items). The obtained results showed high efficiency of the proposed method, surpassing the considered open-source context-biasing approaches in accuracy and decoding speed. Our context-biasing framework is open-sourced as a part of the NeMo toolkit.
@article{arxiv.2508.07014,
title = {TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree},
author = {Andrei Andrusenko and Vladimir Bataev and Lilit Grigoryan and Vitaly Lavrukhin and Boris Ginsburg},
journal= {arXiv preprint arXiv:2508.07014},
year = {2025}
}