论文解读
Sparse Fluid Antenna Arrays: Continuous Position Design Beyond Classical DOF Limits
声源定位 | 7/10
论文速递
论文解读
Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs
社交智能体 | 5.9/10
论文解读
When Vision Speaks for Sound
音视频 | 7.7/10
每日研究速递
语音/音乐/音频论文速递 2026-05-20
共分析 20 篇语音/AI 论文
论文解读
A Distribution Matching Approach to Neural Piano Transcription with Optimal Transport
音乐转录 | 5.5/10
论文解读
A Fast Robust Adaptive filter using Improved Data-Reuse Method
声学回声消除 | 6.2/10
论文解读
A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models
音频修复 | 8.1/10
论文解读
Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
音频安全 | 8.7/10
论文解读
Analyzing Error Propagation in Korean Spoken QA with ASR-LLM Cascades
语音问答 | 5.6/10
论文解读
Audio-Image Cross-Modal Retrieval with Onomatopoeic Images
音频检索 | 7/10
论文解读
Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech
语音摘要 | 7.2/10
论文解读
Bridging the Gap: Converting Read Text to Conversational Dialogue
语音转换 | 3.1/10
论文解读
Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
音频问答 | 6.5/10
论文解读
CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
多模态模型 | 8.6/10
论文解读
Contextual Biasing for Streaming ASR via CTC-based Word Spotting
语音识别 | 7.2/10
论文解读
EnvTriCascade: An Environment-Aware Tri-Stage Cascaded Framework for ESDD2 2026 Challenge
音频深度伪造检测 | 5.3/10
论文解读
Flexible Multi-Channel Target Speaker Extraction Using Geometry-Conditioned Spatially Selective Non-linear Filters
说话人提取 | 6.3/10
论文解读
Fractional-Order Subband p-Norm Adaptive Filter via Transformation Nearest Kronecker Product Decomposition for Active Noise Control
自适应滤波 | 5/10
论文解读
MedASR: An Open-Source Model for High-Accuracy Medical Dictation
语音识别 | 7.9/10
论文解读
MusicDET: Zero-Shot AI-Generated Music Detection
音频深度伪造检测 | 7.4/10