论文解读
Low-Latency Audio Front-End Region-of-Interest Beamforming for Smart Glasses
语音增强 | 7.0/10
多通道
论文解读
Mixture To Beamformed Mixture: Leveraging Beamformed Mixture As Weak-Supervision for Speech Enhancement and Noise-Robust ASR
语音增强 | 8.0/10
论文解读
Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition
语音情感识别 | 7.5/10
论文解读
Neural Network-Based Time-Frequency-Bin-Wise Linear Combination of Beamformers for Underdetermined Target Source Extraction
语音分离 | 7.0/10
论文解读
Qastanet: A DNN-Based Quality Metric for Spatial Audio
空间音频 | 7.5/10
论文解读
SoundCompass: Navigating Target Sound Extraction with Effective Directional Clue Integration in Complex Acoustic Scenes
语音分离 | 7.5/10
论文解读
Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization
说话人分离 | 8.0/10
论文解读
Spectral or Spatial? Leveraging Both for Speaker Extraction in Challenging Data Conditions
语音分离 | 7.0/10
论文解读
Synchronous Secondary Path Modeling and Kronecker-Factorized Adaptive Algorithm for Multichannel Active Noise Control
主动噪声控制 | 7.0/10
论文解读
Theory and Application of Circular Relative Harmonic Coefficients
声源定位 | 7.5/10
论文解读
Earable Platform with Integrated Simultaneous EEG Sensing and Auditory Stimulation
音频事件检测 | 5.5/10
每日研究速递
语音/音乐/音频论文速递 2026-04-27
共分析 13 篇语音/AI 论文
论文解读
Comparison of sEMG Encoding Accuracy Across Speech Modes Using Articulatory and Phoneme Features
这篇论文旨在为无声言语接口（SSI）选择更优的中间表示目标。研究系统比较了发音特征（SPARC）和传统的音素独热编码，在预测表面肌电（sEMG）信号包络上的表现。核心发现是：1）在出声、默语和次发声三种模式下，SPARC特征的编码准确性均显著优于音素特征；2）出声和默语模式的编码性能相当，次发声模式
每日研究速递
语音/音乐/音频论文速递 2026-04-22
共分析 21 篇语音/AI 论文
论文解读
Audio Source Separation in Reverberant Environments using $β$-divergence based Nonnegative Factorization
本文针对混响环境下的多通道音频源分离问题，提出了一种基于β-散度非负因子分解的参数估计新方法。传统方法依赖期望最大化（EM）算法估计源频谱方差和空间协方差矩阵，本文则利用包含源频谱先验信息的基矩阵（可
每日研究速递
语音/音乐/音频论文速递 2026-04-18
共分析 39 篇语音/AI 论文