论文解读
Hierarchical Tokenization of Multimodal Music Data for Generative Music Retrieval
音乐检索 | 7.0/10
生成模型
论文解读
Huí Sù: Co-constructing a Dual Feedback Apparatus
音乐生成 | 5.5/10
论文解读
LLAC: Learned Lossless Audio Codec
音频无损编码 | 7.5/10
论文解读
MAGE: A Coarse-to-Fine Speech Enhancer with Masked Generative Model
语音增强 | 8.0/10
论文解读
MeanFlowSE: One-Step Generative Speech Enhancement via Conditional Mean Flow
语音增强 | 7.5/10
论文解读
MeanSE: Efficient Generative Speech Enhancement with Mean Flows
语音增强 | 6.5/10
论文解读
MECap-R1: Emotion-Aware Policy with Reinforcement Learning for Multimodal Emotion Captioning
语音情感识别 | 7.5/10
论文解读
Noise-to-Notes: Diffusion-Based Generation and Refinement for Automatic Drum Transcription
音乐信息检索 | 8.0/10
论文解读
ParaGSE: Parallel Generative Speech Enhancement with Group-Vector-Quantization-Based Neural Speech Codec
语音增强 | 7.5/10
论文解读
PG-SE: Predictive Acceleration and Correction for Generative Speech Enhancement
语音增强 | 7.5/10
论文解读
Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum
语音合成 | 8.0/10
论文解读
PSTalker: Realistic 3D Talking Head Synthesis via a Semantic-Aware Audio-Driven Point-Based Shape
说话人合成 | 7.5/10
论文解读
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer
音频生成 | 7.0/10
论文解读
SAGA-SR: Semantically and Acoustically Guided Audio Super-Resolution
音频增强 | 7.5/10
论文解读
Timbre-Based Pretraining with Pseudo-Labels for Multi-Instrument Automatic Music Transcription
音乐信息检索 | 7.0/10
论文解读
Tldiffgan: A Latent Diffusion-Gan Framework with Temporal Information Fusion for Anomalous Sound Detection
音频事件检测 | 7.5/10
论文解读
Two-Stage Language Model Framework for Acoustic Echo Cancellation
语音增强 | 7.5/10
论文解读
Uncertainty-Aware 3D Emotional Talking Face Synthesis with Emotion Prior Distillation
音视频 | 8.0/10
论文解读
Wave-Trainer-Fit: Neural Vocoder With Trainable Prior And Fixed-Point Iteration Towards High-Quality Speech Generation From SSL Features
语音合成 | 7.0/10
论文解读
Text-To-Speech with Chain-of-Details: modeling temporal dynamics in speech generation
本文针对文本转语音（TTS）任务，提出了一种名为“细节链”（Chain-of-Details, CoD）的新框架。**要解决的问题**是现有TTS方法在建模语音生成的时域动态（从粗略时序到精细声学细节的渐进过程）方面存在不足。**使用的方法**是将语音生成分解为多个时间分辨率递增的阶段，在每个阶段使