CORTEXA
← Browse
arxiveess.AScs.AI2026-06-29

Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss

Nian Shao, Xian Li, Xiaofei Li

Sound event detection (SED) is a core module for acoustic environmental analysis, yet its performance is often limited by scarce labeled data. Recent systems leverage large pretrained audio foundation models, but effective fine-tuning remains challenging because labeled data are limited while unlabeled data are abundant. A previous work, ATST-SED, addressed this problem with a pseudo-label based semi-supervised fine-tuning framework. In this work, we further improve the framework by adopting an embedding-level self-supervised contrastive loss inspired by ATST-Frame pretraining. This contrastive objective better exploits unlabeled data during fine-tuning. One challenge is that mixup serves different roles in the two objectives: pseudo-label learning uses composition mixup, while contrastive learning treats mixup as a perturbation. To resolve this mismatch, we propose conditional mixup, which combines composition mixup and perturbation mixup in one semi-supervised framework and defines the corresponding embedding-level contrastive losses. The resulting model achieves 0.645 PSDS1 and 0.822 PSDS2 on the DESED validation set, establishing a new state of the art.

View free PDFSource page

Related papers

arxiveess.AScs.AIcs.SD2026-07-18

RealDESED: A Real-World Domestic Sound Event Detection Benchmark

Florian Schmid, Paul Primus, Alexander Fichtinger, Tara Jadidi, Tobias Morocutti, Gerhard Widmer

This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes. Each recording is between 15 and 35 seconds long and contains temporally precise annotations for 15 common do…

View free PDFSource page
arxiveess.AScs.AI2026-07-06

ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions

Thomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez, Jesus Villalba Lopez, Najim Dehak

Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstrea…

View free PDFSource page
arxiveess.AScs.AIcs.SD2026-07-15

Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification

Shiqi Zhang, Tuomas Virtanen

Sound event detection relies on frame-level strong labels whose annotation is expensive. Active learning addresses this problem by selecting the audio segments whose labels help the classifier most. One of the prevailing acquisition strategies for this task, mismatch-first farthe…

View free PDFSource page
arxiveess.AScs.AIcs.CLcs.LGcs.SD2026-07-14

The Sound of Absence: Audio-Language Embedding Models Struggle with Negation

Chun-Yi Kuan, Hung-yi Lee

Audio-language embedding models such as CLAP are widely evaluated on matching present sound events, but rarely on negation. We show this affirmation-only evaluation hides a key limitation: these models fail to encode negated sound concepts, mapping affirmative and negated caption…

View free PDFSource page
arxiveess.AScs.AIeess.SP2026-07-04

Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings

Héctor Martel, Joe Hennessy-Priest, Taemin Cho

Audio foundation models are widely adopted as general-purpose feature extractors, yet the internal structure of their learned representations remains insufficiently understood. In this work, we analyze CLAP audio embeddings through a probing framework, studying the encoding of th…

View free PDFSource page
arxiveess.AScs.AIcs.SD2026-07-15

Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning

Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin, Tuomas Virtanen

Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert annotation and using the labeled segments for training the classifier. The setting is hard: the target calls are extre…

View free PDFSource page