论文解读
A Comparison of SSL-Based Feature Extractors and Back-End Classifiers for Spoofing Detection: A Multi-Corpus Training and Cross-Linguistic Analysis
自监督学习 | 5/10
数据增强
论文解读
Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading
语音合成 | 7.5/10
论文解读
Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model
多模态模型 | 8.2/10
论文解读
Exploring the Scale and Diversity of Speech Anti-spoofing Datasets: Experiments and Analysis
数据增强 | 7.4/10
论文解读
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
音频分类 | 6.9/10
论文解读
Liberating LLM Capabilities in Full-Duplex Speech Models
多模态模型 | 8.7/10
论文解读
MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion
语音转换 | 6.9/10
论文解读
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
语音合成 | 6.5/10
论文解读
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
语音识别 | 7.1/10
论文解读
dots.tts Technical Report
语音合成 | 9/10
论文解读
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
数据增强 | 8.4/10
论文解读
MyGardenBird: A Machine-Learning-Ready Bird Sound Dataset for Twelve Common Malaysian Birds
音频事件检测 | 7.2/10
论文解读
SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models
数据增强 | 5.5/10
论文解读
Towards Event-Robust Acoustic Scene Classification
数据增强 | 6.5/10
论文解读
CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection
语音合成 | 6.5/10
论文解读
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
音频生成 | 7.5/10
论文解读
Channel-Oriented Design for EEG-to-Music Reconstruction
音乐生成 | 7.7/10
论文解读
Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification
音频分类 | 10/10
论文解读
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
语音识别 | 10/10
论文解读
A Training-Efficient Transformer-Based Anti-Spoofing Network for Logical Access in ASVspoof 5
Transformer | 6.7/10