论文解读
TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models
音频理解 | 6.1/10
模型评估
论文解读
Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning
元学习 | 8.1/10
论文解读
Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO
语音交互 | 7.2/10
论文解读
Correlation between prosody and pragmatics: A case study of the discourse marker hālā `now' in Persian
语音属性识别 | 4.4/10
论文解读
Digital Harf: A Clinically Integrated Multimodal AI System for Pervasive Arabic Speech and Language Therapy
语音交互 | 5.6/10
论文解读
Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage
语音识别 | 4.8/10
论文解读
Integrating Contextual Embeddings into Evaluation of Expressive MIDI Piano Performances
音乐理解 | 7.7/10
论文解读
RIPPLE: Generating Multi-Channel Phase, Not Recovering It
音频理解 | 7.1/10
论文解读
SKY-Piano: A Multimodal Piano Performance Dataset
音频理解 | 8.3/10
论文解读
A Study on Online Mask-based Beamforming Using Per-channel Masking for Spatially Distributed Microphones
语音增强 | 5.7/10
论文解读
Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection
语音伪造检测 | 6.6/10
论文解读
Detection of AI-generated stems within hybrid human-AI music
CNN | 6.3/10
论文解读
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues
语音交互 | 6.5/10
论文解读
Explicit Note-Event Tokenization and Pitch-Validity Constrained Decoding for MIDI-to-Tablature Transcription
音乐转录 | 6.1/10
论文解读
Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
音频分类 | 6.8/10
论文解读
MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning
音频字幕生成 | 6.3/10
论文解读
Qwen-Audio-3.0-Gen-Preview Technical Report
音频生成 | 5.6/10
论文解读
Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs
音乐理解 | 6.6/10
论文解读
TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
音视频生成 | 6.7/10
论文解读
Unfolded Recursive Expectation-Maximization Neural Network For Speaker Tracking
声源定位 | 5.4/10