论文解读
StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems
自回归模型 | 9.6/10
音频理解
论文解读
AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
音频检索 | 6.4/10
论文解读
Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants
语音合成 | 7.8/10
论文解读
ITGPT: A Transformer Based Architecture for the Generation of Dance Dance Revolution and In the Groove Charts
音乐生成 | 6.5/10
论文解读
Large Audio Language Models for Spoofing-Aware Speaker Verification
语音伪造检测 | 6.2/10
论文解读
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
音视频生成 | 6.3/10
论文解读
RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems
语音合成 | 7.9/10
论文解读
SceneBind: Binding What and Where Across Vision, Audio and Language
音视频理解 | 6.6/10
论文解读
SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings
语音分离 | 8.1/10
论文解读
Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment
多模态模型 | 5.6/10
论文解读
Video = World + Event Stream
音频理解 | 4.9/10
论文解读
WanSong v1.0 Technical Report
音乐生成 | 7.6/10
论文解读
What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters
音频质量评估 | 7.2/10
论文解读
A Hybrid Mamba for Audio-Visual Navigation
声源定位 | 6.3/10
论文解读
Adapting a Diffusion-Based Music Synthesis Model to Human Voice Conversion
语音转换 | 6.0/10
论文解读
Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation
语音质量评估 | 8.2/10
论文解读
AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning
音视频理解 | 9.2/10
论文解读
Bring Music The Horizon: Music-Driven 360^\circ Video Generation
音视频生成 | 5.3/10
论文解读
Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
音频事件检测 | 6.7/10
论文解读
Do LLMs Need Architectural Changes for Simultaneous Speech Translation? A Prefix-to-Prefix Data Driven Approach
语音翻译 | 5.7/10