Basica, C., Verma, P., Alessandrini, P., & Berceanu, A. (2023). Accessible Co-Creativity with AI through Language and Voice Input. The International Conference on AI and Musical Creativity @ The University of Sussex (AIMC), 2023. Full publication Abstract: This project introduces a set of tools for humans to co-create music with AI-based architectures. The aim is […]
Devansh Zurale, Shlomo Dubnov, Spatial Upsampling of Sparse Head Related Transfer Functions – A VQ-VAE & Transformer based Approach, Audio Engineering Society: AES 2023 International Conference on Spatial and Immersive Audio, U. of Huddersfield, U.K., 2023. Read full publication Abstract: With the increasing demand for AR/VR technologies, enabling accurate reproduction of binaural spatial audio through […]
Paul Lascabettes, Elaine Chew & Isabelle Bloch. Characterizing and Interpreting Music Expressivity through Rhythm and Loudness Simplices, International Computer Music Conference (ICMC 2023), Shenzen, China 2023. Full publication Download publication Abstract: Characterizing and interpreting expressivity in performed music remains an open problem. In this paper, we explore the novel representation of recorded performances of triple […]
Read full publication. Published by Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction. Abstract: In deep learning research, many melody extraction models rely on redesigning neural network architectures to improve performance. In this paper, we propose an input feature modification and a training objective modification based on two assumptions. First, harmonics in […]
Ke Chen, K., Wu, Y., Liu, H., Nezhurina, M., Berg-Kirkpatrick, T., and Dubnov, S., MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies, arXiv preprint,, 2023. doi:10.48550/arXiv.2308.01546. Full publication Download publication Abstract: Diffusion models have shown promising results in cross-modal generation tasks, including text-to-image and text-to-audio generation. However, generating music, as a special type […]
Marco Fiorini, Improvised Musical Interaction with Creative Agents, Aalborg University Copenhagen, Juin 2023 Full publication Download publication Abstract: This thesis was written as the final project of the Master of Science in Sound and Music Computing at Aalborg University Copenhagen. The presented work has been carried out in the Music Representations team at IRCAM – […]
Read full publication. Published by Hao-Wen Dong, Ke Chen, Shlomo Dubnov, Julian McAuley, Taylor Berg-Kirkpatrick. Abstract: Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference. This is partly due to the memory requirements of the lengthy […]
Marc Chemillier (CAMS-EHESS), Yohann Rabearivelo (CAMS-EHESS), Rémi Jaylet (Télécom Paris), contact: chemilli@ehess.fr Read full publication Abstract: In this paper we present a research dealing with musical improvisation practices on TikTok as part of a project devoted to the development of a music improvisation software. Finding musicians to experiment with led us to explore the musical collaborations […]
Yusong Wu, K. Chen, T. Zhang, Y. Hui, T. Berg-Kirkpatrick and S. Dubnov, « Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation, » ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10095969. Full publication Abstract: Contrastive learning has shown remarkable success in the […]
HAo-Wen Dong, K. Chen, S. Dubnov, J. McAuley and T. Berg-Kirkpatrick, « Multitrack Music Transformer, » ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10094628. Full publication Abstract: Existing approaches for generating multitrack music with transformer models have been limited in terms of the […]
