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
论文速递
论文解读
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
论文解读
Archon: A Unified Multimodal Model for Holistic Digital Human Generation
语音合成 | 7.5/10
论文解读
Audio Deepfake Detection with Half-Truth Localisation Using Cross-Attentive Feature Fusion
音频深度伪造检测 | 8.4/10
论文解读
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
多模态模型 | 8.9/10
论文解读
Benchmarking Single-Factor Physical Video-to-Audio Generation
音频生成 | 9/10
论文解读
ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood
语音识别 | 8/10
论文解读
COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings
音频检索 | 6.5/10
论文解读
Data-Efficient On-Policy Distillation for Automatic Speech Recognition
语音识别 | 5.1/10
论文解读
Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding
语音识别 | 6.8/10
论文解读
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
语音合成 | 8.6/10
论文解读
DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation
基准测试 | 9.8/10
论文解读
HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
语音合成 | 8.6/10
论文解读
MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables
语音合成 | 7.3/10
论文解读
Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions
音频分类 | 8.5/10
论文解读
MusTBENCH: Benchmarking and Advancing Temporal Grounding in Music LLMs
音乐生成 | 7.5/10
论文解读
Native Audio-Visual Alignment for Generation
音频生成 | 7.8/10
论文解读
OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants
语音识别 | 7.8/10
论文解读
State-Anchored Complete-View Distillation for Robust Conversational Multimodal Emotion Recognition
语音情感识别 | 8/10
论文解读
The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models
语音识别 | 7/10