Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition

Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as conference presentations. This challenge arises primarily due to constrained model context windows and the sparsity of relevant information within extensive contextual noise. To solve this, we propose the SAP^2 method, a novel framework that dynamically prunes and integrates relevant contextual keywords in two stages. Specifically, each stage leverages our proposed Speech-Driven Attention-based Pooling mechanism, enabling efficient compression of context embeddings while preserving speech-salient information. Experimental results demonstrate state-of-the-art performance of SAP^2 on the SlideSpeech and LibriSpeech datasets, achieving word error rates (WER) of 7.71% and 1.12%, respectively. On SlideSpeech, our method notably reduces biased keyword error rates (B-WER) by 41.1% compared to non-contextual baselines. SAP^2 also exhibits robust scalability, consistently maintaining performance under extensive contextual input conditions on both datasets.

Authors

• Yiming Rong Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences
• Yixin Zhang iFLYTEK Co. , Ltd.
• Ziyi Wang
• Deyang Jiang Institute of Automation, Chinese Academy of Sciences University of Chinese Academy of Sciences
• Yunlong Zhao The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation，Chinese Academy of Sciences, Beijing, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
• Haoran Wu The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation，Chinese Academy of Sciences, Beijing, China Nanjing Artificial Intelligence Research of IA, Nanjing, China
• Shiyu Zhou Institute of Automation, Chinese Academy of Sciences
• Bo Xu Institute of Automation, Chinese Academy of Sciences

Keywords

No keywords are indexed for this paper.