{"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/speechcaps-advancing-instruction-based","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","arxiv_id":"2408.13891","date":"2024-08-25","proceeding":null,"authors":["Chien-yu Huang","Min-Han Shih","Ke-Han Lu","Chi-Yuan Hsiao","Hung-Yi Lee"],"abstract":"Instruction-based speech processing is becoming popular. Studies show that training with multiple tasks boosts performance, but collecting diverse, large-scale tasks and datasets is expensive. Thus, it is highly desirable to design a fundamental task that benefits other downstream tasks. This paper introduces a multi-talker speaking style captioning task to enhance the understanding of speaker and prosodic information. We used large language models to generate descriptions for multi-talker speech. Then, we trained our model with pre-training on this captioning task followed by instruction tuning. Evaluation on Dynamic-SUPERB shows our model outperforming the baseline pre-trained only on single-talker tasks, particularly in speaker and emotion recognition. Additionally, tests on a multi-talker QA task reveal that current models struggle with attributes such as gender, pitch, and speaking rate. The code and dataset are available at https://github.com/cyhuang-tw/speechcaps.","url_abs":"https://arxiv.org/abs/2408.13891v1","url_pdf":"https://arxiv.org/pdf/2408.13891v1.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":"speechcaps-advancing-instruction-based","repo_url":"https://github.com/cyhuang-tw/speechcaps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.13891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}