Neural Controlled Differential Equations

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 10

All topics

Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations
Sep 12, 2026Mattias Cross, Minghui Zhao, Anton RagniNeural Controlled Differential Equations TTS Synthesis
Speech and Hearing Group University of Sheffield Sheffield, United Kingdom
Advances in Neural Controlled Differential Equations
Jul 6, 2026Benjamin WalkerNeural Controlled Differential Equations Neural ODEs
Balliol College, University of Oxford
Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting
Jun 19, 2026Muhammad Bilal Shahid, Zhanhong Jiang, Soumik Sarkar +1Neural Controlled Differential Equations Uncertainty Quantification
Iowa State University, Ames, Iowa, 50011, USA
INDEQS: Informed Neural controlled Differential EQuationS
Jun 17, 2026Michael Detzel, Gabriel Nobis, Kristiyan Blagov +3Neural Controlled Differential Equations Spatiotemporal Forecasting
Fraunhofer Heinrich Hertz Institute · Technische Universität Berlin
Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
May 28, 2026Benjamin Walker, Alexandre Bloch, Lingyi Yang +2Irregular Time-Series Modeling Neural Controlled Differential Equations
Mathematical Institute University of Oxford · School of Mathematical Sciences University of Nottingham · Department of Mathematics, Imperial College London
Universal Time Series Generation with Neural Controlled Differential Equations
May 27, 2026Torben Berndt, Elyes Farjallah, Leif Seute +3Neural Controlled Differential Equations Time Series Generation
Heidelberg Institute for Theoretical Studies, Heidelberg, Germany · IAR, Karlsruhe Institute of Technology, Karlsruhe, Germany · Max Planck Institute for Polymer Research, Mainz, Germany +4
LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
May 11, 2026Sheng Pan, Ming Jin, Bo Du +1Neural Controlled Differential Equations Time Series Forecasting
Griffith University
Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
Feb 2, 2026Egor Serov, Ilya Kuleshov, Alexey ZaytsevEfficient Neural Network Inference Neural Controlled Differential Equations
Applied AI Institute · Risk AI Research Lab
Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
Jan 20, 2026Xu Zhang, Junwei Deng, Chang Xu +2Irregular Time-Series Modeling Neural Controlled Differential Equations
Microsoft Research, Beijing, China · University of Illinois Urbana-Champaign, Illinois, United States · Imperial College London, London, United Kingdom
Certified Robust Invariant Polytope Training in Neural Controlled ODEs
Aug 2, 2024Akash Harapanahalli, Samuel CooganNeural Controlled Differential Equations Robust Control
School of Electrical and Computer Engineering, Georgia Institute of Technology

Sep 12, 2026, cs.SDJ/K move · Enter open · S save

Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations

Mattias Cross, Minghui Zhao, Anton Ragni

Speech and Hearing Group University of Sheffield Sheffield, United Kingdom

Neural Controlled Differential Equations TTS Synthesis Emotional Speech Synthesis

Open paper AskPDF arXiv

Text-to-speech (TTS) models commonly address text--speech alignment by expanding phone-level encoder states to frame-level decoder inputs using predicted durations. While this length-regulation step resolves alignment structurally, this use of duration typically changes only where and how often latent states appear, not the values of the states themselves. This paper proposes a continuous-time mechanism for duration-aware acoustic modelling in TTS using neural controlled differential equations (CDEs). We formulate the phone representation as a temporally parameterised control path and use a neural acoustic vector field to produce a continuous-time hidden state whose values evolve with phonetic content and duration-derived timing. The resulting trajectory can be sampled at discrete points and integrated into a standard acoustic decoder pipeline. Objective results contrast CDEs and typical recurrent models. Subjective results suggest that CDE-based models evaluating one phone per step can improve rank-order agreement between synthesised and reference emotion intensity while maintaining comparable emotion-expression quality to a strong baseline. Additional experiments with half-phone step-sizes suggest that temporal resolution changes the trade-off between style tracking and absolute calibration. These results position CDEs as a promising design space for continuous-time and duration-aware style-sensitive TTS.

Momentum

Related topics

Latest papers 10