CORTEXA
← Browse
arxiveess.AScs.LG2026-07-03

Open-Set Source Tracing as Compositional Factors via Structured Prototypes

Santiago Rubio, Antonio Almudévar, Antonio Miguel, Eduardo Lleida, Alfonso Ortega

Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech. However, current research often equates a "source" with its generative architecture. We propose redefining a source as a compositional tuple of Architecture, Training Data, and other training factors affecting the generated speech. We propose a framework using Structured Orthonormal Prototypes to minimize class overlap and intra-class variance. Our Subspace Partitioning strategy splits the embedding into architecture and data subspaces, while a residual subspace captures stochastic variability, enabling "compositional generalization" for novel factor combinations. This approach improves performance for partially seen sources and maintains robustness in fully open-set scenarios. MLAAD evaluations for Few-Shot open-set Identification show our approach significantly outperforms angular-margin baselines.

View free PDFSource page

Related papers

arxiveess.AScs.LG2026-07-01

Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes

Yanxiong Li, Jiaxin Tan, Qianqian Li, Guoqing Chen, Sen Huang, Tuomas Virtanen

Most existing audio classification methods suppose that each query (testing) sample belongs to a class of support (training) samples, and misrecognize samples of unseen classes as seen classes (cannot reject samples of unseen classes). In this study, we propose a method for Few-s…

View free PDFSource page
arxiveess.AScs.LGcs.SD2026-07-03

Deriving Benchmarking Datasets from Long-Form Recordings: Challenges and Opportunities

Kaveri K. Sheth, Lawrence Borst, Tarek Kunze, Marvin Lavechin, Okko Räsänen, Sho Tsuji, et al.

Long-form recordings (LFRs) of child-centered audio are ecologically valid sources for studying early language development, but three problems limit their use. First, LFR corpora are collected across sites with heterogeneous formats and consent structures, making cross-corpus use…

View free PDFSource page
arxivcs.SDcs.LGeess.AS2026-07-17

Fretiq: Browser-Native Electric Guitar String Classification via Engineered Spectral Features and Held-Out Free-Play Evaluation

Aadi Garg

Identifying which string produces a given pitch in monophonic electric guitar audio is a fundamental classification challenge: a single pitch can often be produced on multiple strings at different fret positions, with timbral differences that prior listening studies confirm are l…

View free PDFSource page
arxivcs.SDcs.LGeess.ASeess.SPmath.NA2026-07-20

FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration

Ali Boudaghi, Hadi Zare

Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music…

View free PDFSource page
arxivcs.CLcs.AIcs.LGcs.SDeess.AS2026-06-26

Do Speech Emphasis Models Generalize across Languages and Emotions?

Megan Wei, Deepali Aneja, Jiaqi Su, Yunyun Wang, Haonan Chen, Zeyu Jin

Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech. We introduce MMEE (Multilingual Multi-Emotion Emphasis), a corpus of 10,000 professionally record…

View free PDFSource page