论文解读
LightAVSeg: Lightweight Audio-Visual Segmentation
模型压缩 | 6.3/10
知识蒸馏
论文解读
REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation
音视频生成 | 7.3/10
论文解读
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
知识蒸馏 | 7/10
论文解读
A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification
音频分类 | 4.9/10
论文解读
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation
知识蒸馏 | 10/10
论文解读
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
知识蒸馏 | 6.7/10
论文解读
End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
端到端 | 7/10
论文解读
Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach
说话人验证 | 9.1/10
论文解读
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
语音合成 | 6.7/10
论文解读
Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs
语音合成 | 7.4/10
论文解读
Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection
多模态模型 | 7.4/10
论文解读
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
音频分类 | 8.7/10
论文解读
Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification
说话人识别 | 8.6/10
论文解读
Fast Speech Foundation Model Distillation Using Interleaved Stacking
知识蒸馏 | 6.6/10
论文解读
AuRA: Internalizing Audio Understanding into LLMs as LoRA
语音问答 | 7.5/10
论文解读
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
语音识别 | 7.5/10
论文解读
USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding
音频编码 | 9/10
论文解读
Logit Distillation on Manifolds: Mapping by Learning
语音识别 | 6.5/10
论文解读
Raon-Speech Technical Report
语音识别 | 6.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-30
共分析 6 篇语音/AI 论文