Logo image
Back
A Neural Model for Contextual Biasing Score Learning and Filtering
Conference proceeding

A Neural Model for Contextual Biasing Score Learning and Filtering

Wanting Huang and Weiran Wang
2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.1-7
12/06/2025
DOI: 10.1109/ASRU65441.2025.11433843

View Online

Abstract

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for candidate phrases based on acoustic information extracted by an ASR encoder, which can be used to filter out unlikely phrases and to calculate bonus for shallow-fusion biasing. We introduce a per-token discriminative objective that encourages higher scores for ground-truth phrases while suppressing distractors. Experiments on the Librispeech biasing benchmark show that our method effectively filters out majority of the candidate phrases, and significantly improves recognition accuracy under different biasing conditions when the scores are used in shallow fusion biasing. Our approach is modular and can be used with any ASR system, and the filtering mechanism can potentially boost performance of other biasing methods.
 Data Mining Automatic speech recognition Benchmark testing Computational modeling Conferences Context modeling contextual biasing Decoding Information filters Matched filters phrase filtering shallow-fusion biasing Training

Details

Metrics

1 Record Views
Logo image