每日研究速递
语音/音乐/音频论文速递 2026-06-25
共分析 27 篇语音/AI 论文
实时处理
论文解读
Next-Turn: Duration-Aware Streaming Endpoint Detection via Time-to-Next-Speech-Onset Prediction
语音合成 | 7.9/10
论文解读
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
语音分离 | 8.4/10
论文解读
Time Segmented Beamforming via Dynamic Programming: Theory and Implementation
实时处理 | 7.7/10
每日研究速递
语音/音乐/音频论文速递 2026-05-26
共分析 27 篇语音/AI 论文
论文解读
StepAudio 2.5 Technical Report
统一音频模型 | 8.3/10
每日研究速递
语音/音乐/音频论文速递 2026-05-25
共分析 19 篇语音/AI 论文
论文解读
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
语音对话系统 | 6.9/10
论文解读
SIREM: Speech-Informed MRI Reconstruction with Learned Sampling
医学图像重建 | 7.3/10
论文解读
Real-time Speech Restoration using Data Prediction Mean Flows
音频修复 | 7.5/10
论文解读
Physics-Based iOCT Sonification for Real-time Interaction Awareness in Subretinal Injection
医疗音频 | 6.5/10
论文解读
Streaming Speech-to-Text Translation with a SpeechLLM
语音翻译 | 6.8/10
论文解读
Online Segmented Beamforming via Dynamic Programming
声源定位 | 6.0/10
论文解读
LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation
多模态压缩 | 8.5/10
论文解读
Hearing the Ocean: Bio-inspired Gammatone-CNN framework for Robust Underwater Acoustic Target Classification
音频分类 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-07
共分析 22 篇语音/AI 论文
论文解读
Can Speech LLMs Think while Listening?
语音对话系统 | 7.5/10
论文解读
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 7.0/10
论文解读
Knowing When to Quit: Probabilistic Early Exits for Speech Separation Networks
语音分离 | 7.0/10
论文解读
TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
多模态模型 | 7.0/10