[PDF][PDF] ATEPP: A dataset of automatically transcribed expressive piano performance
Computational models of expressive piano performance rely on attributes like tempo, timing,
dynamics and pedalling. Despite some promising models for performance assessment and …
dynamics and pedalling. Despite some promising models for performance assessment and …
Differentiable piano model for MIDI-to-audio performance synthesis
Recent neural-based synthesis models have achieved impressive results for musical
instrument sound generation. In particular, the Differentiable Digital Signal Processing …
instrument sound generation. In particular, the Differentiable Digital Signal Processing …
Virtual Instrument Performances (VIP): A Comprehensive Review
T Kyriakou, MÁ de la Campa Crespo… - Computer Graphics …, 2024 - Wiley Online Library
Driven by recent advancements in Extended Reality (XR), the hype around the Metaverse,
and real‐time computer graphics, the transformation of the performing arts, particularly in …
and real‐time computer graphics, the transformation of the performing arts, particularly in …
The chamber ensemble generator: Limitless high-quality mir data via generative modeling
Data is the lifeblood of modern machine learning systems, including for those in Music
Information Retrieval (MIR). However, MIR has long been mired by small datasets and …
Information Retrieval (MIR). However, MIR has long been mired by small datasets and …
Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting
H Kim, S Choi, J Nam - ICASSP 2024-2024 IEEE International …, 2024 - ieeexplore.ieee.org
Synthesizing performing guitar sound is a highly challenging task due to the polyphony and
high variability in expression. Recently, deep generative models have shown promising …
high variability in expression. Recently, deep generative models have shown promising …
An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
X Jin, W Zhou, J Wang, D Xu, Y Zheng - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Computational aesthetic evaluation has made remarkable contribution to visual art works,
but its application to music is still rare. Currently, subjective evaluation is still the most …
but its application to music is still rare. Currently, subjective evaluation is still the most …
DDSP-Piano: A neural sound synthesizer informed by instrument knowledge
Instrument sound synthesis using deep neural networks has received numerous
improvements over the last couple of years. Among them, the Differentiable Digital Signal …
improvements over the last couple of years. Among them, the Differentiable Digital Signal …
RealSinger: Ultra-realistic singing voice generation via stochastic differential equations
Z Shi, S Wu - Neurocomputing, 2024 - Elsevier
Synthesizing high-quality singing voice from music score is a challenging problem in music
generation and has many practical applications. Samples generated by existing singing …
generation and has many practical applications. Samples generated by existing singing …
Can Knowledge of End-to-End Text-to-Speech Models Improve Neural Midi-to-Audio Synthesis Systems?
X Shi, E Cooper, X Wang, J Yamagishi… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
With the similarity between music and speech synthesis from symbolic input and the rapid
development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve …
development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve …
Expressive piano performance rendering from unpaired data
Recent advances in data-driven expressive performance rendering have enabled automatic
models to reproduce the characteristics and the variability of human performances of …
models to reproduce the characteristics and the variability of human performances of …