Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.11139 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912842413768704 |
|---|---|
| author | Rong, Yiming Zhang, Yixin Wang, Ziyi Jiang, Deyang Zhao, Yunlong Wu, Haoran Zhou, Shiyu Xu, Bo |
| author_facet | Rong, Yiming Zhang, Yixin Wang, Ziyi Jiang, Deyang Zhao, Yunlong Wu, Haoran Zhou, Shiyu Xu, Bo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition Rong, Yiming Zhang, Yixin Wang, Ziyi Jiang, Deyang Zhao, Yunlong Wu, Haoran Zhou, Shiyu Xu, Bo Computation and Language 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. |
| title | Speech-Aware Long Context Pruning and Integration for Contextualized Automatic Speech Recognition |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.11139 |