arXiv AI
Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 2
MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment
arXiv:2605. 29987v2 Announce Type: replace Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse.
arXiv Machine Learning
Aug 31
Rethinking Speaker Embeddings for Speech Generation: Sub-Center Modeling for Capturing Intra-Speaker Diversity
arXiv:2407.04291v4 Announce Type: replace-cross Abstract: Modeling speech variation is key to natural, expressive generation. Speaker embeddings are commonly used to condition personalized speech sys...
arXiv AI
Jun 11
Quality Adaptive Angular Margin Learning for Respiratory Sound Classification
arXiv:2606. 11915v1 Announce Type: cross Abstract: We present a quality-adaptive angular-margin learning framework that improves feature generalization by enforcing intra-class compactness and inter-class separability.
arXiv Computation and Language
Aug 21
Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
arXiv:2603. 21875v2 Announce Type: replace-cross Abstract: Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting source embeddings are independent of speaker traits.
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.
arXiv Computation and Language
3d ago
VOSSA: Voiceprint Optimization for Streaming Speech Architectures
arXiv:2609.38887v1 Announce Type: cross Abstract: Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effect...