Category Research

On 14-19 April, several AIM researchers will participate at the 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024). ICASSP is the leading conference in the field of signal processing and the flagship event of the IEEE Signal Processing Society.As in previous years, the UKRI Centre for Doctoral Training in AI and Music will have a strong presence at the conference, both in terms of numbers and overall impact. The below papers presented at ICASSP 2024 are authored or co-authored by AIM students:

• High resolution guitar transcription via domain adaptation, by Xavier Riley, Drew Edwards, and Simon Dixon
• Bass accompaniment generation via latent diffusion, by Marco Pasini, Maarten Grachten, and Stefan Lattner
• Unsupervised pitch-timbre disentanglement of musical instruments using a Jacobian disentangled sequential autoencoder, by Yin-Jyun Luo, Sebastian Ewert, and Simon Dixon
• Posterior variance-parameterised Gaussian dropout: improving disentangled sequential autoencoders for zero-shot voice conversion, by Yin-Jyun Luo and Simon Dixon
• Mertech: instrument playing technique detection using self-supervised pretrained model with multi-task finetuning, by Dichucheng Li, Yinghao Ma, Weixing Wei, Qiuqiang Kong, Yulun Wu, Mingjin Che, Fan Xia, Emmanouil Benetos, and Wei Li
• Syncfusion: Multimodal Onset-Synchronized Video-to-Audio Foley Synthesis, by Marco Comunità, Riccardo F. Gramaccioni, Emilian Postolache, Emanuele Rodolà, Danilo Comminiello, and Joshua D. Reiss

The following paper will be presented at the ICASSP Workshop on Explainable Machine Learning for Speech and Audio:

• Explainable modeling of gender-targeting practices in toy advertising sound and music, by Luca Marinelli and Charalampos Saitis

See you all at ICASSP!

On 5-9 November 2023, several AIM researchers will participate at the 24th International Society for Music Information Retrieval Conference (ISMIR 2023). ISMIR is the leading conference in the field of music informatics, and is currently the top-cited publication for Music & Musicology (source: Google Scholar). This year ISMIR will take place in Milan, Italy, and online.

This year, the AI and Music CDT is involved in the organisation of the conference, while also having a strong presence at the tutorials and scientific programme of the conference.

In the Scientific Programme, the following papers are authored/co-authored by AIM students:

• Real-time Percussive Technique Recognition and Embedding Learning for the Acoustic Guitar (Andrea Martelloni, Andrew McPherson, Mathieu Barthet)
• Symbolic Music Representations for Classification Tasks: A Systematic Evaluation (Huan Zhang, Emmanouil Karystinaios, Simon Dixon, Gerhard Widmer, Carlos Eduardo Cancino-Chacón)
• LyricWhiz: Robust Multilingual Lyrics Transcription by Whispering to ChatGPT (Le Zhuo, Ruibin Yuan, Jiahao Pan, Yinghao Ma, Yizhi Li, Ge Zhang, Si Liu, Roger B. Dannenberg, Jie Fu, Chenghua Lin, Emmanouil Benetos, Wenhu Chen, Wei Xue, Yike Guo)
• On the effectiveness of speech self-supervised learning for music (Yinghao Ma, Ruibin Yuan, Yizhi Li, Ge Zhang, Chenghua Lin, Xingran Chen, Anton Ragni, Hanzhi Yin, Emmanouil Benetos, Norbert Gyenge, Ruibo Liu, Gus Xia, Roger B. Dannenberg, Yike Guo, Jie Fu)
• Singing voice synthesis using differentiable LPC and glottal-flow inspired wavetables (Chin-Yun Yu, George Fazekas) – best paper award finalist
• FiloBass: A Dataset and Corpus Based Study of Jazz Basslines (Xavier Riley, Simon Dixon)
• Gender-coded sound: Analysing the gendering of music in toy commercials via multi-task learning (Luca Marinelli, George Fazekas, Charalampos Saitis)
• Modeling Harmonic Similarity for Jazz Using Co-occurrence Vectors and the Membrane Area (Carey Bunks, Simon Dixon, Tillman Weyde, Bruno Di Giorgi)

The following Tutorials will be presented by AIM students:

• Introduction to Differentiable Audio Synthesizer Programming (Ben Hayes, Jordie Shier, Chin-Yun Yu, David Südholt, Rodrigo Diaz)
• Transformer-based Symbolic Music Generation: Fundamentals to Advanced Concepts, Stylistic Considerations, Conditioning Mechanisms and Large Language Models (Berker Banar, Pedro Sarmento, Sara Adkins)
• Kymatio: Deep Learning meets Wavelet Theory for Music Signal Processing (Cyrus Vahidi, Christopher Mitcheltree, Vincent Lostanlen)

On Satellite Events, AIM PhD student Elona Shatri is general co-chair for the 5th International Workshop on Reading Music Systems (WoRMS 2023). Additionally, she will showcase two papers she collaborated on with master’s students: Towards Artificially Generated Handwritten Sheet Music Datasets (Pranjali Hande, Elona Shatri, Benjamin Timms, and George Fazekas) Improving Sheet Music Recognition using Data Augmentation and Image Enhancement (Zihui Zhang, Elona Shatri, and George Fazekas)

Finally, AIM PhD student Ilaria Manco is Sponsorship/Industry co-chair for ISMIR 2023.

See you at ISMIR!