论文解读
Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence
基础模型 | 6.8/10
自监督学习
论文解读
Exploring Token-Space Manipulation in Latent Audio Tokenizers
音频编码 | 6.5/10
论文解读
PoDAR: Power-Disentangled Audio Representation for Generative Modeling
语音合成 | 7.3/10
论文解读
Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation
语音增强 | 7.2/10
论文解读
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
世界模型 | 5.0/10
论文解读
BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing
BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing
论文解读
MultiLinguahah : A New Unsupervised Multilingual Acoustic Laughter Segmentation Method
音频事件检测 | 8.5/10
论文解读
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
音频编码 | 7.0/10
论文解读
WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling
语音生成 | 7.5/10
论文解读
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
音乐评估 | 7.5/10
论文解读
SEI-SHIELD: Robust Specific Emitter Identification Under Label Noise Via Self-Supervised Filtering and Iterative Rescue
信号处理 | 7.5/10
论文解读
Stage-adaptive audio diffusion modeling
音频生成 | 7.0/10
论文解读
A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
语音识别 | 7.0/10
论文解读
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
音乐理解 | 8.0/10
论文解读
Contrastive Regularization for Accent-Robust ASR
语音识别 | 7.5/10
论文解读
Deepfake Audio Detection Using Self-supervised Fusion Representations
音频深度伪造检测 | 7.5/10
论文解读
Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework
说话头伪造检测 | 7.5/10
论文解读
Learning Generalizable Action Representations via Pre-training AEMG
生物声学 | 7.5/10
论文解读
Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings
音频深度伪造检测 | 7.0/10
论文解读
Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
多模态模型 | 7.0/10