论文解读
I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
语音合成 | 6.5/10
论文速递
论文解读
LoSATok: Low-dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation
语音合成 | 7/10
论文解读
MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
语音生成 | 9.9/10
论文解读
OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation
音频检索 | 9.2/10
论文解读
Robust Quantum-MUSIC for DoA Estimation Using Rydberg Atomic Receiver Arrays
Robust Quantum-MUSIC for DoA Estimation Using Rydberg Atomic Receiver Arrays
论文解读
SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
语音情感识别 | 8.7/10
论文解读
TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
语音识别 | 10/10
论文解读
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
语音合成 | 8/10
论文解读
Utilizing Missed Detections in Directional Sensitivity-Based DOA Estimation
语音识别 | 7.1/10
论文解读
VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding
音频问答 | 7.0/10
论文解读
When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR
语音识别 | 10/10
论文解读
Why We Need Speech to Evaluate Speech Translation
语音翻译 | 8.3/10
每日研究速递
语音/音乐/音频论文速递 2026-05-28
共分析 30 篇语音/AI 论文
论文解读
A Multimodal Framework for Dementia Detection via Linguistic and Acoustic Representation Learning
多模态模型 | 7.7/10
论文解读
An investigation of AI integration in sound designer workflows and experiences
An investigation of AI integration in sound designer workflows and experiences
论文解读
AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models
多模态模型 | 9.7/10
论文解读
Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy
自监督学习 | 8.1/10
论文解读
Can We Hear from Events? Generating Speech from Event Camera
语音合成 | 7.8/10
论文解读
CFMDCTCodec: A Low-Bitrate Neural Speech Codec with Noise-Prior-aware Conditional Flow Matching for MDCT-Spectral Enhancement
语音编码 | 8.4/10
论文解读
Continual Speaker Identity Unlearning with Minimal Interference
语音合成 | 8.3/10