{"ID":6267039,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-13T01:02:08.706470581Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08117","arxiv_id":"2607.08117","title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","abstract":"Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speech-augmented language models (SLMs) in complex multi-entity scenarios. Considering the inherent context-window limitations of SLMs, identifying relevant target entities from a large-scale biasing list is crucial for effective recognition. To this end, COALA maps SLM latent representations into a specialized discriminative space to quantify the matching intensity between audio segments and candidate entities. Furthermore, we address the training collapse in prior study when handling multi-target utterances-where multiple rare words co-occur. Experimental results on the LibriSpeech benchmark demonstrate that COALA consistently achieves superior contextual biasing performance across various biasing list scales.","short_abstract":"Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speech-augmented language models (SLMs) in co...","url_abs":"https://arxiv.org/abs/2607.08117","url_pdf":"https://arxiv.org/pdf/2607.08117v1","authors":"[\"Jhih-Rong Guo\",\"Bi-Cheng Yan\",\"Tien-Hong Lo\",\"Berlin Chen\"]","published":"2026-07-09T05:26:22Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}