{"ID":23475240,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.20121","arxiv_id":"2609.20121","title":"Alignment-Path Distillation from Non-streaming ASR-LLMs for Streaming Speech Recognition","abstract":"In this paper, we propose an alignment-path distillation framework for streaming automatic speech recognition (ASR) with large language models (LLMs). Interleaved streaming ASR-LLMs use forced alignments (FA) from alignment models, such as those trained with connectionist temporal classification (CTC), to construct speech-text training sequences. However, alignments obtained from a separate acoustic model may be inconsistent with those learned by LLM-based ASR. This motivates us to transfer alignment information from a non-streaming ASR-LLM to improve streaming recognition. Specifically, we extract monotonic alignment paths from a non-streaming teacher's soft text-audio attention and use them to construct interleaved training sequences. The framework also includes logit and hidden-state distillation to learn from the teacher's output distributions and internal representations. Experimental results show that, without logit or hidden-state distillation, training with teacher-derived alignment paths achieves a 5.2% relative error rate reduction compared with training using forced alignments. When both models use logit and hidden-state distillation, teacher-derived alignments yield a 3.9% relative error rate reduction, with similar mean emission latency but higher flicker. The complete framework achieves a 16.6% relative error rate reduction compared with training using forced alignments without logit or hidden-state distillation.","short_abstract":"In this paper, we propose an alignment-path distillation framework for streaming automatic speech recognition (ASR) with large language models (LLMs). Interleaved streaming ASR-LLMs use forced alignments (FA) from alignment models, such as those trained with connectionist temporal classification (CTC), to construct spe...","url_abs":"https://arxiv.org/abs/2609.20121","url_pdf":"https://arxiv.org/pdf/2609.20121v1","authors":"[\"Yan Jia\",\"Kai Huang\",\"Junjie Chen\",\"Feng-Long Xie\",\"Xu Tang\",\"Yao Hu\"]","published":"2026-09-17T12:18:40Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}