News

On 10-16 December, several AIM researchers will participate at the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), taking place in New Orleans, USA. NeurIPS is a world-leading conference in AI, machine learning, and computational neuroscience, attracting more than ten thousand attendees annually. The AI and Music centre for doctoral training will have a strong presence at NeurIPS 2023.

In the Main Conference and specifically its Datasets and Benchmarks track, the following paper is authored by AIM members:

• MARBLE: Music Audio Representation Benchmark for Universal Evaluation (Ruibin Yuan, Yinghao Ma, Yizhi Li, Ge Zhang, Xingran Chen, Hanzhi Yin, Zhuo Le, Yiqi Liu, Jiawen Huang, Zeyue Tian, Binyue Deng, Ningzhi Wang, Chenghua Lin, Emmanouil Benetos, Anton Ragni, Norbert Gyenge, Roger Dannenberg, Wenhu Chen, Gus Xia, Wei Xue, Si Liu, Shi Wang, Ruibo Liu, Yike Guo, Jie Fu)

In the NeurIPS Machine Learning for Audio Workshop:

• AIM PhD student Ben Hayes is giving an invited talk on Differentiable digital signal processing (DDSP).

And the following papers are authored by AIM members:

• The Song Describer dataset: a corpus of audio captions for music-and-language evaluation (Ilaria Manco, Benno Weck, SeungHeon Doh, Minz Won, Yixiao Zhang, Dmitry Bodganov, Yusong Wu, Ke Chen, Philip Tovstogan, Emmanouil Benetos, Elio Quinton, George Fazekas, Juhan Nam)
• Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates (Marco Pasini, Stefan Lattner, George Fazekas)

See you at NeurIPS!