Jinhua Liang

Machine learning, signal processing, audio understanding.

Conference & journal paper

✉ denotes the corresponding author

  • Jiehui Jia, Huan Zhang, Jinhua Liang. (2024) “Bridging Discrete and Continuous: A Multimodal Strategy for Complex Emotion Detection”, in peer review.
  • Tanisha Hisariya, Huan Zhang, Jinhua Liang. (2024) “Bridging Paintings and Music – Exploring Emotion based Music Generation through Paintings”, in peer review.
  • Wen Qing Lim Jinhua Liang Huan Zhang. (2024) “Hierarchical Symbolic Pop Music Generation with Graph Neural Networks”, in peer review.
  • Huan Zhang, Shreyan Chowdhury, Carlos Eduardo Cancino-Chacˊon, Jinhua Liang, Simon Dixon, Gerhard Widmer. (2024) “DExter: Learning and Controlling Performance Expression with Diffusion Models. Applied Sciences. 14(15):6543.”
  • Huan Zhang, Jinhua Liang, Simon Dixon. (2024) “From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano”, International Society of Music Information Retrieval (ISMIR).
  • Jinhua Liang, Ines Nolasco, Burooj Ghani, Huy Phan, Emmanouil Benetos, Dan Stowell. (2024) “Mind the Domain Gap: a Systematic Analysis on Bioacoustic Sound Event Detection” European Signal Processing Conference (EUSIPCO) on Signal Analysis for Biodiversity.
  • Jinhua Liang, Huan Zhang, Haohe Liu, Yin Cao, Qiuqiang Kong, Xubo Liu, Wenwu Wang, Mark D. Plumbley, Huy Phan, Emmanouil Benetos. (2024) “WavCraft: Audio Editing and Generation with Natural Language Prompts”, International Conference on Learning Representations (ICLR) 2024 Workshop on LLM Agents.
  • Xubo Liu, Zhongkai Zhu, Haohe Liu, Yi Yuan, Meng Cui, Qiushi Huang, Jinhua Liang, Yin Cao, Quiqiang Kong, Mark D. Plumbley, Wenwu Wang. “Wavjourney: Compositional audio creation with large language models”, in Peer Review.
  • Jinhua Liang, Huy Phan, and Emmanouil Benetos. (2024) “Learning from Taxonomy: Multi-Label Few-Shot Classification for Everyday Sound Recognition”, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 771-775, doi: 10.1109/ICASSP48485.2024.10446908. [post] [link]
  • Jinhua Liang, Xubo Liu, Haohe Liu, Huy Phan, Emmanouil Benetos, Mark D. Plumbley, Wenwu Wang. “Adapting Language-Audio Models as Few-Shot Audio Learners” (accepted by INTERSPEECH 2023). [post] [link]
  • Yi Yuan, Haohe Liu, Jinhua Liang, Xubo Liu, Mark D. Plumbley, Wenwu Wang. “Leveraging Pre-trained AudioLDM for Sound Generation: A Benchmark Study” (accepted by EUSIPCO 2023). [link]
  • Liang, J., Phan, H., & Benetos, E. (2022). Leveraging Label Hierachies for Few-Shot Everyday Sound Recognition. Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022). Nancy, France.
  • Li, R., Liang, J., & Phan, H. (2022). Few-Shot Bioacoustic Event Detection: Enhanced Classifiers for Prototypical Networks. Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022). Nancy, France.
  • Tao Zhang, Jinhua Liang✉, and Guoqing Feng. “Adaptive time-frequency feature resolution network for acoustic scene classification.” Applied Acoustics 195 (2022): 108819.
  • Tao Zhang, Shuang Li, Guoqing Feng, Jinhua Liang✉, Lun He, Xin Zhao. “Local channel transformation for efficient convolutional neural network.” Signal, Image and Video Processing (2022): 1-9.
  • Jinhua Liang, Huy Phan, and Emmanouil Benetos. “Everyday Sound Recognition with Limited Annotations” Digital Music Research Network (DMRN +16), 2021.
  • Zhang, T., Feng, G., Liang, J., & An, T. (2021). “Acoustic scene classification based on Mel spectrogram decomposition and model merging,” in Applied Acoustics, 182, 108258.
  • J. Liang, T. Zhang✉ and G. Feng, “Channel Compression: Rethinking Information Redundancy Among Channels in CNN Architecture,” in IEEE Access, vol. 8, pp. 147265-147274, 2020, doi: 10.1109/ACCESS.2020.3015714. [post] [link]
  • Tao Zhang, Jinhua Liang✉, and Biyun Ding, “Acoustic scene classification using deep cnn with fine-resolution feature”, Expert Systems with Applications, vol. 143, pp. 113067, 2020. post [link]

Technical report

  • Andrew Mitchell, Jinhua Liang, et al. “Deep Learning Techniques for Noise Annoyance Detection”, Data Study Group, the Alan Turing Institute, Dec. 20, 2022.
  • Ren Li, Jinhua Liang, Huy Phan. “FEW-SHOT BIOACOUSTIC EVENT DETECTION USING PROTOTYPICAL NETWORKS WITH RESNET CLASSIFIER”, DCASE2022 Challenge, June 2022.
  • Guoqing Feng, Jinhua Liang, and Biyun Ding, “Acoustic Scene Classification Based on Lightweight CNN With Efficient Convolutions,” Tech. Rep., DCASE2020 Challenge, June 2020.
  • Biyun Ding, Ganjun Liu, and Jinhua Liang, “Acoustic Scene Classification Based on Ensemble System,” Tech. Rep., DCASE2019 Challenge, June 2019.