Publications

2025

1. F-StrIPE: Fast Structure-informed Positional Encoding for Music Generation

   Manvi Agarwal, Changhong Wang, and Gael Richard

   IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP), 2025

   Bib PDF

   @article{agarwal2025structure,
     title = {F-StrIPE: Fast Structure-informed Positional Encoding for Music Generation},
     author = {Agarwal, Manvi and Wang, Changhong and Richard, Gael},
     journal = {IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP)},
     year = {2025},
     demo = {https://www.manviagarwal.com/projects/faststructurepe/}
   }

2. Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects

   Victor Deng, Changhong Wang, Gael Richard, and Brian McFee

   IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP), 2025

   Bib PDF Code

   @article{deng2025investigating,
     title = {Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects},
     author = {Deng, Victor and Wang, Changhong and Richard, Gael and McFee, Brian},
     journal = {IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP)},
     year = {2025},
   }

2024

1. Structure-informed Positional Encoding for Music Generation

   Manvi Agarwal, Changhong Wang, and Gael Richard

   IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP), 2024

   Bib PDF Code

   @article{agarwal2024structure,
     title = {Structure-informed Positional Encoding for Music Generation},
     author = {Agarwal, Manvi and Wang, Changhong and Richard, Gael},
     journal = {IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP)},
     year = {2024},
   }

2023

1. Transfer Learning and Bias Correction with Pre-trained Audio Embeddings.

   Changhong Wang, Gaël Richard, and  Brian McFee

   International Society for Music Information Retrieval (ISMIR), 2023

   Bib PDF Code

   @article{wang2023transfer,
     title = {Transfer Learning and Bias Correction with Pre-trained Audio Embeddings.},
     author = {Wang, Changhong and Richard, Gaël and and Brian McFee},
     journal = {International Society for Music Information Retrieval (ISMIR)},
     year = {2023},
   }

2. Explainable Audio Classification of Playing Techniques with Layer-wise Relevance Propoagation

   Changhong Wang, Vincent Lostanlen, and  Mathieu Lagrange

   IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP), 2023

   Bib PDF Code

   @article{wang2023explainable,
     title = {Explainable Audio Classification of Playing Techniques with Layer-wise Relevance Propoagation},
     author = {Wang, Changhong and Lostanlen, Vincent and and Mathieu Lagrange},
     journal = {IEEE International Conference on Acoustics and Speech and and Signal Processing (ICASSP)},
     year = {2023},
   }

3. Mesostructures: Beyond Spectrogram Loss in Differentiable Time-Frequency Analysis

   Cyrus Vahidi, Han Han, Changhong Wang, Mathieu Lagrange, György Fazekas, and Vincent Lostanlen

   Journal of the Audio Engineering Society (AES), 2023

   Bib PDF Code

   @article{vahidi2023mesostructures,
     title = {Mesostructures: Beyond Spectrogram Loss in Differentiable Time-Frequency Analysis},
     author = {Vahidi, Cyrus and Han, Han and Wang, Changhong and Lagrange, Mathieu and Fazekas, György and Lostanlen, Vincent},
     journal = {Journal of the Audio Engineering Society (AES)},
     year = {2023},
   }

2022

1. Differentiable Time-Frequency Scattering on GPU

   John Muradeli, Cyrus Vahidi, Changhong Wang, Han Han, Vincent Lostanlen, Mathieu Lagrange, and 1 more author

   International Conference on Digital Audio Effects (DAFx), 2022

   Best Paper Award Bib PDF Code

   Best Paper Award

   @article{muradeli2022differentiable,
     title = {{Differentiable Time-Frequency Scattering on GPU}},
     author = {Muradeli, John and Vahidi, Cyrus and Wang, Changhong and Han, Han and Lostanlen, Vincent and Lagrange, Mathieu and and György Fazekas},
     journal = {International Conference on Digital Audio Effects (DAFx)},
     year = {2022},
     demo = {https://cyrusvahidi.github.io/jtfs-gpu/},
   }

2. Adaptive Scattering Transforms for Playing Technique Recognition

   Changhong Wang, Emmanouil Benetos, Vincent Lostanlen, and  Elaine Chew

   IEEE/ACM Transactions on Audio and Speech and and Language Processing (TASLP), 2022

   Bib PDF

   @article{wang2022adaptive,
     title = {Adaptive Scattering Transforms for Playing Technique Recognition},
     author = {Wang, Changhong and Benetos, Emmanouil and Lostanlen, Vincent and and Elaine Chew},
     journal = {IEEE/ACM Transactions on Audio and Speech and and Language Processing (TASLP)},
     year = {2022},
     dataset = {https://zenodo.org/record/5744336/}
   }

3. Joint Scattering for Automatic Chick Call Recognition

   Changhong Wang, Emmanouil Benetos, Shuge Wang, and Elisabetta Versace

   IEEE European Signal Processing Conference (EUSIPCO), 2022

   Bib PDF Code

   @article{wang2022joint,
     title = {Joint Scattering for Automatic Chick Call Recognition},
     author = {Wang, Changhong and Benetos, Emmanouil and Wang, Shuge and Versace, Elisabetta},
     journal = {IEEE European Signal Processing Conference (EUSIPCO)},
     year = {2022},
     dataset = {https://zenodo.org/record/6655837}
   }

2021

1. Violinist Identification Based on Vibrato Features

   Yudong Zhao, Changhong Wang, György Fazekas, Emmanouil Benetos, and Mark Sandler

   European Signal Processing Conference (EUSIPCO), 2021

   Bib PDF

   @article{zhao2021violinist,
     title = {Violinist Identification Based on Vibrato Features},
     author = {Zhao, Yudong and Wang, Changhong and Fazekas, György and Benetos, Emmanouil and Sandler, Mark},
     journal = {European Signal Processing Conference (EUSIPCO)},
     year = {2021},
   }

2020

1. Playing Technique Recognition by Joint Time-Frequency Scattering

   Changhong Wang, Vincent Lostanlen, Emmanouil Benetos, and Elaine Chew

   IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

   Bib PDF

   @article{wang2020playing,
     title = {Playing Technique Recognition by Joint Time-Frequency Scattering},
     author = {Wang, Changhong and Lostanlen, Vincent and Benetos, Emmanouil and Chew, Elaine},
     journal = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
     year = {2020},
     dataset = {https://zenodo.org/record/3776864/}
   }

2019

1. Adaptive Time-Frequency Scattering for Periodic Modulation Recognition in Music Signals

   Changhong Wang, Emmanouil Benetos, Vincent Lostanlen, and Elaine Chew

   International Society for Music Information Retrieval (ISMIR), 2019

   Bib PDF

   @article{wang2019adaptive,
     title = {Adaptive Time-Frequency Scattering for Periodic Modulation Recognition in Music Signals},
     author = {Wang, Changhong and Benetos, Emmanouil and Lostanlen, Vincent and Chew, Elaine},
     journal = {International Society for Music Information Retrieval (ISMIR)},
     year = {2019},
     dataset = {https://zenodo.org/record/3776864/}
   }

2. HMM-based Glissando Detection for Recordings of Chinese Bamboo Flute

   Changhong Wang, Emmanouil Benetos, Xiaojie Meng, and Elaine Chew

   Sound and Music Computing Conference (SMC), 2019

   Bib PDF

   @article{wang2019hmm,
     title = {HMM-based Glissando Detection for Recordings of Chinese Bamboo Flute},
     author = {Wang, Changhong and Benetos, Emmanouil and Meng, Xiaojie and Chew, Elaine},
     journal = {Sound and Music Computing Conference (SMC)},
     year = {2019},
     dataset = {https://zenodo.org/record/3776864/}
   }