The paper introduces the Conditional Neural Manifold (CNM), a data‑driven replacement for the fixed array manifold used in subspace methods like MUSIC. CNM learns a mapping from source parameters to steering vectors conditioned on observed snapshots, using an encoder to produce a latent scene representation that drives a neural field over the parameter space. By shaping the resulting MUSIC landscape, CNM restores super‑resolution performance under array imperfections, colored noise, correlated sources, near‑field propagation, and resolves the angle‑frequency ambiguity without requiring steering‑vector supervision.
By Julian P. Merkofer, Vincent van de Schaft, Ruud J. G. van Sloun
arXiv:2606. 18664v1 Announce Type: cross Abstract: Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments.
By Yizhuo Yang, Junqiao Fan, Shenghai Yuan, Lihua Xie
Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic environments. Classical methods such as Multiple Signal Classification (MUSIC) offer strong theoretical foundations but degrade under low signal-to-noise ratios.
arXiv:2607. 04471v1 Announce Type: cross Abstract: Linear spatial filters (beamformers) enable robust, generalizable and interpretable speech enhancement with performance guarantees under ideal parameterization.
By Jakob Kienegger, Tal Peer, Sina Khanagha, Timo Gerkmann
arXiv:2609.23152v1 Announce Type: cross
Abstract: Recently proposed self-supervised audio encoders learn powerful general-purpose representations of sound scenes, yet they are spatially blind. To sup...
By Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden
The paper introduces TSR-ITNR, a two‑stage, self‑supervised framework for hyperspectral image super‑resolution that fuses high‑resolution multispectral and low‑resolution hyperspectral data. Stage 1 refines an implicit Tucker representation using a low‑rank spatial tensor and spectral basis, enhanced by a pretrained denoiser, to capture fine spatial details and spectral correlations. Stage 2 applies parameter‑free calibration to extract complementary corrections from both observations, preserving geometry and ensuring orthogonal complementarity, leading to superior reconstruction quality demonstrated on benchmark datasets and improved downstream segmentation performance.
By Liqian Yang, Xingchi Chen, Xinfeng Gui, Xiangyong Cao, Qianxin Yi
arXiv:2606. 12282v1 Announce Type: cross Abstract: Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes.
By Dmitrii Gavrilev
arXiv:2511. 05350v3 Announce Type: replace-cross Abstract: We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptually motivated losses, yields encodings that are structured according to a perceptual hierarchy.
By Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer
arXiv:2608. 15037v1 Announce Type: cross Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference.
By Ashish Anand Shukla, Rini Smita Thakur, Aryan Das, Vinod K. Kurmi
The paper introduces a supervised end-to-end benchmark for restoring orchestral historical music, addressing the lack of ground-truth pairs in early‑20th‑century recordings. It simulates the historical degradation process more accurately than prior work and trains a latent flow‑matching model that surpasses existing HMR baselines in various evaluations. Additionally, the authors release a 9.3‑hour license‑free test set, code, and audio demos for the community.
By Steven Cho, Junghyun Koo, Raphael Lafargue, Tushar Dhyani, Eloi Moliner, Yuki Mitsufuji
arXiv:2608.29867v1 Announce Type: new
Abstract: Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear enc...
By Louen Pottier, Louis Lesueur, Anders Thorin
arXiv:2607. 03641v1 Announce Type: cross Abstract: The manifold hypothesis posits that high-dimensional data are concentrated near a low-dimensional embedded manifold.
By Zelong Bi, Amuchechukwu Ibenegbu, Sarat Moka