论文解读
Improving the performance of an ASV system using hybrid speech features
说话人验证 | 5.0/10
Transformer
论文解读
Instruct-FD: Can Your Full-Duplex Speech System Follow Turn-Taking Instructions?
语音交互 | 7.2/10
论文解读
Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness
音频水印 | 6.4/10
论文解读
SCoPE: Shift-Aware Speaker-Conditioned Priors for Emotion Recognition in Conversations
语音情感识别 | 6.0/10
论文解读
TF-MossFormer: Integrating Convolution Gated Local-Global Attentions for Enhanced Time-Frequency Domain Monaural Speech Separation
语音分离 | 6.3/10
论文解读
Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores
语音伪造检测 | 7.0/10
论文解读
Word meaning co-determines vowel-inherent spectral change. A corpus-based investigation of conversational Mandarin
语音属性识别 | 5.9/10
论文解读
X^3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
音频理解 | 7.1/10
每日研究速递
语音/音乐/音频论文速递 2026-07-24
共分析 18 篇语音/AI 论文
论文解读
A Diagnostic Evaluation Framework for AI-Generated Cover Songs Using Music-Theoretic and Acoustic Features
音频质量评估 | 8.0/10
论文解读
Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
音频理解 | 6.8/10
论文解读
Black-Box Optimization for Identifying and Inverting Audio Dynamic Range Control Effects
音频理解 | 4.0/10
论文解读
Cross-Subject Semantic Decoding with Shared-Space Alignment for Generalized Neural Representation Learning
语音交互 | 6.3/10
论文解读
Improved Monitoring of Honey bee Colony Strength via Audio IoT Sensors, Modulation Tensorgrams and Recurrent Neural Networks
音频事件检测 | 6.3/10
论文解读
Layer-Wise Decision Fusion for Fake Audio Detection Using XLS-R
音频理解 | 7.5/10
论文解读
Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction
Transformer | 7.5/10
论文解读
Multimodal Speaker Verification as a Threat to Speaker Anonymization
说话人验证 | 9.2/10
论文解读
OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
音视频理解 | 6.9/10
论文解读
RIME: Enabling Large-Scale Agentic Post-Production
大语言模型 | 7.6/10
论文解读
RPPNet: Perceptually-Grouped Rhythm-Pitch Primitives for Long-Term Structure Melody Generation via Boundary-Aware Modeling
音乐生成 | 6.9/10