论文解读
Transcript-Free Lightweight Detection of Alzheimer's Disease from Spontaneous Speech Using Handcrafted MFCC-Dominant Acoustic Biomarkers
语音属性识别 | 4.9/10
论文速递
论文解读
Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR
语音识别 | 7.2/10
论文解读
Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation
音乐生成 | 6.0/10
论文解读
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
语音伪造检测 | 8.1/10
论文解读
WaveNet-Style Guitar Amplifier Model Pruning for Real-Time iOS Deployment
音频生成 | 8.0/10
论文解读
What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection
语音伪造检测 | 6.6/10
论文解读
Where Speech Enhancement Hurts Recognition: An Inference Time Polar Projection Diagnosis
语音识别 | 6.7/10
论文解读
Which Languages Transfer Best to Warlpiri? A Similarity-Based Study for Low-Resource ASR
语音识别 | 6.5/10
每日研究速递
语音/音乐/音频论文速递 2026-07-14
共分析 53 篇语音/AI 论文
论文解读
Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models
音视频理解 | 6.0/10
论文解读
Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations
音频理解 | 7.3/10
论文解读
Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering
多模态模型 | 7.1/10
论文解读
Event-Based Token Sequences for Audio-Conditioned Music-Game Level Modeling
音乐生成 | 7.2/10
论文解读
FreyaTTS Technical Report
语音合成 | 7.7/10
论文解读
Immersive Social Interaction with VR and LLM-Assisted Humanoids
语音交互 | 4.7/10
论文解读
Optimal Transport-based Semantic Alignment for LLM-based Audio-Visual Speech Recognition
音视频语音识别 | 6.9/10
论文解读
Phone Segmentation and Recognition through Phonological Activation Mapping
语音识别 | 7.7/10
论文解读
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
语音合成 | 7.5/10
论文解读
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesitancy Recognition
音视频理解 | 6.4/10
论文解读
Technical Report for MERL's Real-TSE Challenge Submission
语音分离 | 6.6/10