Speech, audio and music processing with LLM; Speech-based multimodal large language model with multitask ability; New architectures for LLM-based ASR and LLM-based speech and audio generation; Utilizing LLM for speech, audio and spoken language data processing; Leveraging multilingual LLM for multilingual or low-resource speech processing; Paralinguistics and speech emotion application with LLM; Cognitive science and EEG processing with LLM; Pre-training, supervised fine-tuning and alignment for speech language model; Parameter-efficient fine-tuning and prompt tuning for speech language model; Speech processing with LLM in healthcare and education scenarios; Self-supervised representation learning on speech, audio and music.
本议题截稿时间为 7月20日,具体投稿信息请参见投稿指南页面,热烈欢迎投稿。
链接:http://www.iscslp2024.com/submission
Longbiao Wang, Tianjin University Hung-yi Lee, National Taiwan University Xie Chen, Shanghai Jiao Tong University Xixin Wu, The Chinese University of Hong Kong Tianrui Wang, Tianjin University Ziyang Ma, Shanghai Jiao Tong University
