George Fazekas

40 papers A* 1Journal 24Unranked 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
Diffusion Timbre Transfer Via Mutual Information Guided Inpainting.
CoRR
Ching Ho Lee, Javier Nistal, Stefan Lattner, Marco Pasini, George Fazekas
2026 A* conf
Visualising Pianists' Touch: Transcribing Expressive Piano Performance from Audio to Piano Key Motion.
CHI
Jingjing Tang, Shinichi Furuya, Hayato Nishioka, Momoko Shioki, Geraint A. Wiggins, George Fazekas, Vincent K. M. Cheung
2025 — conf
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio.
ISMIR
Marco Pasini, Stefan Lattner, George Fazekas
2025 J jnl
CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2025 — conf
GD-Retriever: Controllable generative text-music retrieval with diffusion models.
ISMIR
Julien Guinot, Elio Quinton, George Fazekas
2025 — conf
MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling.
ISMIR
Jingjing Tang, Xin Wang, Zhe Zhang, Junichi Yamagishi, Geraint A. Wiggins, George Fazekas
2025 J jnl
MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling.
CoRR
Jingjing Tang, Xin Wang, Zhe Zhang, Junichi Yamagishi, Geraint A. Wiggins, George Fazekas
2025 J jnl
Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2025 — conf
SLAP: Siamese Language-Audio Pretraining without negative samples for Music Understanding.
ISMIR
Julien Guinot, Alain Riou, Elio Quinton, George Fazekas
2025 J jnl
Towards An Integrated Approach for Expressive Piano Performance Synthesis from Music Scores.
CoRR
Jingjing Tang, Erica Cooper, Xin Wang, Junichi Yamagishi, George Fazekas
2025 J jnl
Towards a Unified Representation Evaluation Framework Beyond Downstream Tasks.
CoRR
Christos Plachouras, Julien Guinot, George Fazekas, Elio Quinton, Emmanouil Benetos, Johan Pauwels
2024 J jnl
Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation.
CoRR
Marco Pasini, Javier Nistal, Stefan Lattner, George Fazekas
2024 — conf
Diff-MST: Differentiable Mixing Style Transfer.
ISMIR
Soumya Sai Vanka, Christian J. Steinmetz, Jean-Baptiste Rolland, Joshua D. Reiss, George Fazekas
2024 J jnl
Diff-MST: Differentiable Mixing Style Transfer.
CoRR
Soumya Sai Vanka, Christian J. Steinmetz, Jean-Baptiste Rolland, Joshua D. Reiss, George Fazekas
2024 J jnl
Diff-MSTC: A Mixing Style Transfer Prototype for Cubase.
CoRR
Soumya Sai Vanka, Lennart Hannink, Jean-Baptiste Rolland, George Fazekas
2024 J jnl
Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation.
CoRR
Elona Shatri, George Fazekas
2024 J jnl
Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approach.
CoRR
Elona Shatri, Daniel Raymond, George Fazekas
2024 — conf
MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models.
ISMIR
Benno Weck, Ilaria Manco, Emmanouil Benetos, Elio Quinton, George Fazekas, Dmitry Bogdanov
2024 J jnl
MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models.
CoRR
Benno Weck, Ilaria Manco, Emmanouil Benetos, Elio Quinton, George Fazekas, Dmitry Bogdanov
2024 — conf
Music2Latent: Consistency Autoencoders for Latent Audio Compression.
ISMIR
Marco Pasini, Stefan Lattner, George Fazekas
2024 J jnl
Music2Latent: Consistency Autoencoders for Latent Audio Compression.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2024 — conf
Semi-Supervised Contrastive Learning of Musical Representations.
ISMIR
Julien Guinot, Elio Quinton, George Fazekas
2024 J jnl
Synthesising Handwritten Music with GANs: A Comprehensive Evaluation of CycleWGAN, ProGAN, and DCGAN.
CoRR
Elona Shatri, Kalikidhar Palavala, George Fazekas
2024 — conf
Tidal MerzA: Combining affective modelling and autonomous code generation through Reinforcement Learning.
AIMC
Elizabeth Wilson, George Fazekas, Geraint A. Wiggins
2023 J jnl
Adoption of AI Technology in the Music Mixing Workflow: An Investigation.
CoRR
Soumya Sai Vanka, Maryam Safi, Jean-Baptiste Rolland, George Fazekas
2023 J jnl
An Comparative Analysis of Different Pitch and Metrical Grid Encoding Methods in the Task of Sequential Music Generation.
CoRR
Yuqiang Li, Shengchen Li, George Fazekas
2023 — conf
General Purpose Audio Effect Removal.
WASPAA
Matthew Rice, Christian J. Steinmetz, George Fazekas, Joshua D. Reiss
2023 J jnl
General Purpose Audio Effect Removal.
CoRR
Matthew Rice, Christian J. Steinmetz, George Fazekas, Joshua D. Reiss
2023 J jnl
JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting.
CoRR
Eleanor Row, Jingjing Tang, George Fazekas
2023 J jnl
Reconstructing Human Expressiveness in Piano Performances with a Transformer Network.
CoRR
Jingjing Tang, Geraint A. Wiggins, George Fazekas
2023 J jnl
Self-Supervised Music Source Separation Using Vector-Quantized Source Category Estimates.
CoRR
Marco Pasini, Stefan Lattner, George Fazekas
2023 — conf
SketchSynth: a browser-based sketching interface for sound control.
NIME
Sebastian Löbbers, George Fazekas
2022 — conf
ATEPP: A Dataset of Automatically Transcribed Expressive Piano Performance.
ISMIR
Huan Zhang, Jingjing Tang, Syed Rm Rafee, Simon Dixon, George Fazekas, Geraint A. Wiggins
2022 J jnl
Differentiable Time-Frequency Scattering in Kymatio.
CoRR
John Muradeli, Cyrus Vahidi, Changhong Wang, Han Han, Vincent Lostanlen, Mathieu Lagrange, George Fazekas
2022 — conf
How Music features and Musical Data Representations Affect Objective Evaluation of Music Composition: A Review of CSMT Data Challenge 2020.
ISMIR
Yuqiang Li, Shengchen Li, George Fazekas
2021 J jnl
An Exploratory Study on Perceptual Spaces of the Singing Voice.
CoRR
Brendan D. O'Connor, Simon Dixon, George Fazekas
2021 — conf
Ontology based Machine Learning in Semantic Audio Applications - Abstract.
ISIC
George Fazekas
2021 J jnl
Zero-shot Singing Technique Conversion.
CoRR
Brendan D. O'Connor, Simon Dixon, George Fazekas
2020 — conf
An Exploratory Study on Perceptual Spaces of the Singing Voice.
AIMC
Brendan O'Connor, Simon Dixon, George Fazekas
2020 J jnl
Timbre Space Representation of a Subtractive Synthesizer.
CoRR
Cyrus Vahidi, George Fazekas, Charalampos Saitis, Alessandro Palladini