arXiv Machine Learning July 21, 2026 By Ysobel Sims, Alexandre Mendes, Stephan Chalup

A Benchmark of Generative Methods for Zero-Shot Environmental Sound Classification

Read the original on arXiv Machine Learning →

arXiv:2412. 03771v4 Announce Type: replace-cross Abstract: Zero-shot learning enables models to generalise to unseen classes using semantic information, bridging the gap between training classes and previously unseen test classes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Embedding-Space Diffusion for Zero-Shot Environmental Sound Classification

arXiv:2412. 03771v3 Announce Type: replace-cross Abstract: Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes.

By Ysobel Sims, Alexandre Mendes, Stephan Chalup

rag diffusion computer-vision benchmarks safety

arXiv AI

Jun 2

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.

By Maris Basha, Anja Zai, Sabine Stoll, Richard Hahnloser

rag multimodal benchmarks safety

arXiv AI

Sep 7

SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds

SCAPES is a lightweight, resource‑efficient generative model that synthesizes high‑fidelity environmental sounds with high‑level semantic control. It operates on the continuous latent manifold of a neural audio codec, using a segmentation strategy and a Continuous Normalizing Flow to model latent trajectories. A 36‑million‑parameter instance can be trained on limited, uncurated data with a single consumer‑grade GPU, achieving convergence in roughly twice the source audio duration and enabling smooth semantic interpolation.

By Esteban Guti\'errez, Lonce Wyse, Frederic Font, Xavier Serra

diffusion computer-vision nlp

arXiv AI

Jun 4

SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification

arXiv:2605. 13672v1 Announce Type: cross Abstract: Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues.

By Giries Abu Ayoub, Morad Tukan, Loay Mualem

computer-vision benchmarks

arXiv Machine Learning

Aug 6

Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation

arXiv:2608. 04902v1 Announce Type: cross Abstract: Video-to-audio (V2A) generation extends image-to-audio generation (I2A) by introducing consecutive frames that provide essential temporal cues for audio synthesis.

By Zehua Chen, Junyou Wang, Yuxuan Jiang, Zhenying Fang, Yusheng Dai, Jianfei Chen, Ziwei Liu, Jun Zhu

diffusion multimodal benchmarks

arXiv AI

Sep 16

Sample-Conditioned Representation Selection for Audio Few-Shot Learning

arXiv:2609.17076v1 Announce Type: new Abstract: Few-shot audio classifiers may rely on foreground-background co-occurrences and fail when those correlations shift. On SpurAudio, the resulting represe...

By Fengrui Liu, Ningxin Shen, Yi Li, Yiwei Fu, Feng Liu, Jiangmeng Li

One email a morning, machine-written

Related stories

Embedding-Space Diffusion for Zero-Shot Environmental Sound Classification

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds

SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification

Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation

Sample-Conditioned Representation Selection for Audio Few-Shot Learning