论文解读
DepthTalk: Few-Shot Talking Head Generation with Depth-Aware 3D Gaussian Field Motion
说话人生成 | 7.0/10
Icassp-2026
论文解读
Detecting and Attributing Synthetic Spanish Speech: The HISPASpoof Dataset
语音伪造检测 | 7.5/10
论文解读
DGSDNet: Dual-Graph Spectral Diffusion Network for Incomplete Multimodal Emotion Recognition in Conversations
语音情感识别 | 8.0/10
论文解读
Diff-vs: Efficient Audio-Aware Diffusion U-Net for Vocals Separation
语音分离 | 7.5/10
论文解读
Diffemotalk: Audio-Driven Facial Animation with Fine-Grained Emotion Control via Diffusion Models
语音情感识别 | 7.5/10
论文解读
Differentiable Grouped Feedback Delay Networks for Learning Direction and Position-Dependent Late Reverberation
空间音频 | 7.5/10
论文解读
Differentiable Pulsetable Synthesis for Wind Instrument Modeling
音乐生成 | 7.5/10
论文解读
Diffusion Timbre Transfer via Mutual Information Guided Inpainting
音乐生成 | 7.5/10
论文解读
Direct Preference Optimization For Speech Autoregressive Diffusion Models
语音合成 | 7.5/10
论文解读
Direct Simultaneous Translation Activation for Large Audio-Language Models
语音翻译 | 6.0/10
论文解读
Direct Transfer of Prosody in Speech-to-speech Translation using Disentangled Speech Tokens
语音翻译 | 7.5/10
论文解读
Directly Trained Spiking Neural Networks with Adaptive Phase Coding
音频分类 | 7.0/10
论文解读
DisContSE: Single-Step Diffusion Speech Enhancement based on Joint Discrete and Continuous Embeddings
语音增强 | 8.5/10
论文解读
Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens
语音合成 | 7.5/10
论文解读
Discrete-Continuous Fusion With Adaptive Hierarchical Features For Audio Deepfake Detection
音频深度伪造检测 | 8.0/10
论文解读
Disentangled Authenticity Representation for Partially Deepfake Audio Localization
音频深度伪造检测 | 6.5/10
论文解读
Disentangling Physiology from Fidelity: Latent-Guided Diffusion Models for Cross-Modal Cardiac Synthesis
音频生成 | 7.5/10
论文解读
Dissecting Performance Degradation in Audio Source Separation under Sampling Frequency Mismatch
音乐源分离 | 7.5/10
论文解读
DISSR: Disentangling Speech Representation for Degradation-Prior Guided Cross-Domain Speech Restoration
语音增强 | 7.5/10
论文解读
Distilling Attention Knowledge for Speaker Verification
说话人验证 | 8.0/10