论文解读
Assessing Identity Leakage in Talking Face Generation: Metrics and Evaluation Framework
说话人脸生成 | 7.5/10
基准测试
论文解读
Audio-Visual Deepfake Generation and Detection: An Exploratory Survey
音频深度伪造检测 | 6.5/10
论文解读
Auditory Illusion Benchmark for Large Audio Language Models
模型评估 | 7.0/10
论文解读
Benchmarking Music Autotagging with MGPHot Expert Annotations vs. Generic Tag Datasets
音乐信息检索 | 7.5/10
论文解读
Beyond Face Swapping: A Diffusion-Based Digital Human Benchmark for Multimodal Deepfake Detection
音频深度伪造检测 | 8.1/10
论文解读
Can Large Audio Language Models Understand Audio Well? Speech, Scene and Events Understanding Benchmark for LALMs
基准测试 | 7.0/10
论文解读
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
基准测试 | 7.0/10
论文解读
Combining SSL Speech Features, Contextual Transformers and Mamba Models for Realistic Audio Spoofing Detection
音频深度伪造检测 | 7.5/10
论文解读
Content-Preserving Speech Representation Learning Via Adaptive Segment-Level Alignment
语音识别 | 7.5/10
论文解读
CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content
跨模态检索 | 6.5/10
论文解读
Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music
语音识别 | 7.0/10
论文解读
Cross-Lingual Interleaving for Speech Language Models
语音大模型 | 7.5/10
论文解读
Do Bias Benchmarks Generalise? Evidence from Voice-Based Evaluation of Gender Bias in Speechllms
模型评估 | 8.0/10
论文解读
EchoFake: A Replay-Aware Dataset For Practical Speech Deepfake Detection
音频深度伪造检测 | 8.5/10
论文解读
Enhancing Audio Question-Answering Performance Through Log-Likelihood Guided Reward Functions
音频问答 | 8.5/10
论文解读
Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations
模型评估 | 7.0/10
论文解读
Evaluating Compositional Structure in Audio Representations
模型评估 | 7.0/10
论文解读
Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech
语音情感识别 | 7.5/10
论文解读
Evaluating Pretrained Speech Embedding Systems for Dysarthria Detection Across Heterogenous Datasets
语音生物标志物 | 7.5/10
论文解读
Face-Voice Association with Inductive Bias for Maximum Class Separation
说话人验证 | 7.0/10