Browsing School of Electronic Engineering and Computer Science by Author "Guo, Y"

Now showing items 1-9 of 9

    • Can LLMs "Reason" in Music? An Evaluation of LLMs' Capability of Music Understanding and Generation 

      Zhou, Z; Wu, Y; Wu, Z; Zhang, X; Yuan, R; Ma, Y; Wang, L; Benetos, E; Xue, W; Guo, Y (2024-11-10)
      Symbolic Music, akin to language, can be encoded in discrete symbols. Recent research has extended the application of large language models (LLMs) such as GPT-4 and Llama2 to the symbolic music domain including understanding ...

    • ChatMusician: Understanding and Generating Music Intrinsically with LLM 

      Yuan, R; Lin, H; Wang, Y; Tian, Z; Wu, S; Shen, T; Zhang, G; Wu, Y; Liu, C; Zhou, Z (2024-08-11)
      While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity’s creative language. We introduce ChatMusician, an open-source ...

    • ComposerX: Multi-Agent Symbolic Music Composition with LLMs 

      Deng, Q; Yang, Q; Yuan, R; Huang, Y; Wang, Y; Liu, X; Tian, Z; Pan, J; Zhang, G; Lin, H (2024-11-10)
      Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints. Current LLMs often ...

    • Identifying divergent design thinking through the observable behavior of service design novices 

      Hu, Y; Du, X; Bryan-Kinns, N; Guo, Y (2018-10-15)
      © 2018, Springer Nature B.V. Design thinking holds the key to innovation processes, but is often difficult to detect because of its implicit nature. We undertook a study of novice designers engaged in team-based design ...

    • LyricWhiz: Robust Multilingual Lyrics Transcription by Whispering to ChatGPT 

      Zhuo, L; Yuan, R; Pan, J; Ma, Y; Li, Y; Zhang, G; Liu, S; Dannenberg, R; Fu, J; Lin, C (International Society for Music Information Retrieval Conference (ISMIR), 2023-11-05)
      We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock ...

    • MARBLE: Music Audio Representation Benchmark for Universal Evaluation 

      Yuan, R; Ma, Y; Li, Y; Zhang, G; Chen, X; Yin, H; Zhuo, L; Liu, Y; Huang, J; Tian, Z (37th Conference on Neural Information Processing Systems (NeurIPS), 2023)
      In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is ...

    • MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training 

      Li, Y; Yuan, R; Zhang, G; Ma, Y; Chen, X; Yin, H; Xiao, C; Lin, C; Ragni, A; Benetos, E (2024-05-07)
      Self-supervised learning (SSL) has recently emerged as a promising paradigm for training generalisable models on large-scale data in the fields of vision, text, and speech. Although SSL has been proven effective in speech ...

    • Mobile App Squatting 

      Hu, Y; Wang, H; He, R; Li, L; Tyson, G; Castro, I; Guo, Y; Wu, L; Xu, G; Web Conference (WWW)

    • On the effectiveness of speech self-supervised learning for music 

      Ma, Y; Yuan, R; Li, Y; Zhang, G; Chen, X; Yin, H; Lin, C; Benetos, E; Ragni, A; Gyenge, N (International Society for Music Information Retrieval Conference (ISMIR), 2023-11-05)
      Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR) still remains largely unexplored. While ...