{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/speechprune-context-aware-token-pruning-for","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","arxiv_id":"2412.12009","date":"2024-12-16","proceeding":null,"authors":["Yueqian Lin","Yuzhe Fu","Jingyang Zhang","Yudong Liu","Jianyi Zhang","Jingwei Sun","Hai \"Helen\" Li","Yiran Chen"],"abstract":"We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately 90-second spoken inputs. While current Speech LLMs excel at short-form tasks, they struggle with the computational and representational demands of longer audio sequences. To address this limitation, we propose SpeechPrune, a training-free token pruning strategy that uses speech-text similarity and approximated attention scores to efficiently discard irrelevant tokens. In SPIRAL, SpeechPrune achieves accuracy improvements of 29% and up to 47% over the original model and the random pruning model at a pruning rate of 20%, respectively. SpeechPrune can maintain network performance even at a pruning level of 80%. This approach highlights the potential of token-level pruning for efficient and scalable long-form speech understanding.","url_abs":"https://arxiv.org/abs/2412.12009v2","url_pdf":"https://arxiv.org/pdf/2412.12009v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"speechprune-context-aware-token-pruning-for","repo_url":"https://github.com/linyueqian/spiral_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.12009","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}