会员服务
SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning
Arxiv
0+阅读 · 6月20日
An Effective Strategy for Modeling Score Ordinality and Non-uniform Intervals in Automated Speaking Assessment
Arxiv
0+阅读 · 6月22日
How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures
Arxiv
0+阅读 · 6月20日
Evaluating self-supervised echocardiographic representations across downstream extraction strategies for left-ventricular segmentation and ejection fraction estimation
Arxiv
0+阅读 · 6月22日
Towards Detecting Neural Audio Codec Synthesized Heart Sounds
Arxiv
0+阅读 · 6月19日
SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
Arxiv
0+阅读 · 6月19日
When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning
Arxiv
0+阅读 · 6月18日
Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models
Arxiv
0+阅读 · 6月12日
Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors
Arxiv
0+阅读 · 6月13日
Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
Arxiv
0+阅读 · 6月10日
SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space
Arxiv
0+阅读 · 6月9日
Leveraging Soft Distributions of SSL-Derived Discrete Speech Tokens for Downstream Inference
Arxiv
0+阅读 · 6月5日
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
Arxiv
0+阅读 · 6月10日
BAT: Better Audio Transformer Guided by Convex Gated Probing
Arxiv
0+阅读 · 5月29日
MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio
Arxiv
0+阅读 · 5月22日
参考链接
微信扫码咨询专知VIP会员
Top