OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
This work addresses the challenge of rare word recognition in speech recognition for users of systems like OWSM, but it is incremental as it builds on existing contextual biasing methods.
The paper tackled the problem of speech foundation models struggling to recognize rare and unseen words in automatic speech recognition by integrating contextual biasing with a pre-trained model while freezing its parameters. The result was an 11.6-point improvement in biasing word error rate and a 0.9-point overall WER improvement with a 7.5% reduction in real-time factor on the LibriSpeech test set.
Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words. While contextual biasing (CB) is a promising approach to improve recognition of such words, most CB methods are trained from scratch, resulting in lower performance than SFMs due to the lack of pre-trained knowledge. This paper integrates an existing CB method with OWSM v3.1 while freezing its pre-trained parameters. By leveraging the knowledge embedded in SFMs, the proposed method enables effective CB while preserving the advantages of SFMs, even with a small dataset. Experimental results show that the proposed method improves the biasing word error rate (B-WER) by 11.6 points, resulting in a 0.9 point improvement in the overall WER while reducing the real-time factor by 7.5% compared to the non-biasing baseline on the LibriSpeech 100 test-clean set.