Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition
This addresses the problem of domain-specific contextualized ASR for scenarios like conference presentations, representing a novel method for a known bottleneck.
The paper tackles the challenge of leveraging long-context information in contextualized automatic speech recognition, proposing the SAP² method that dynamically prunes and integrates relevant contextual keywords, achieving state-of-the-art word error rates of 7.71% on SlideSpeech and 1.12% on LibriSpeech, with a 41.1% reduction in biased keyword error rates on SlideSpeech.
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.