论文解读
在喇叭与犬吠同时响起时听清人声：VAANI 如何把印度田野噪声钉在时间轴上
语音识别 | 5.8/10
语音增强
论文解读
开耳助听器里漏进来的噪声，为何要让扬声器自己去抵消？
语音增强 | 7.5/10
论文解读
相位不再复用：当 Transformer 学会看懂复数谱图
语音增强 | 6.4/10
论文解读
干净本身成了开关：当语音增强的理想输出反噬自身
语音增强 | 6.4/10
论文解读
把循环拆成并行：用时带混合与自适应回退让增强前端不再拖累识别
语音增强 | 6.2/10
论文解读
听得更干净，却想得更错：当语音增强把大模型带偏
语音增强 | 8.0/10
论文解读
相位越不准，幅度越要背锅：用频带加权把流式增强从过衰减里拉回来
语音增强 | 6.4/10
论文解读
把去噪塞进耳蜗编码器里：用稀疏脉冲换六倍能耗
语音增强 | 6.7/10
论文解读
不用再把 PDM 翻译成 PCM：让状态空间模型直接听懂单比特麦克风
语音增强 | 7.5/10
论文解读
既要指向性，又要去混响：一次前向如何重建干净的虚拟方向麦克风
空间音频 | 5.3/10
论文解读
LipsAM: Lipschitz-continuous Neural Networks for Convergent Plug-and-Play Audio Signal Recovery
音频修复 | 10.0/10
论文解读
SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networks
语音增强 | 7.6/10
论文解读
Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement
语音增强 | 9.0/10
论文解读
μNet: Ultra-Low-Memory and Low-Complexity Speech Enhancement for Embedded Digital Signal Processors
语音增强 | 8.3/10
论文解读
A Novel Binaural Cue Preservation Loss for DNN-Based Binaural Speech Enhancement
语音增强 | 5.6/10
论文解读
Feedforward Active Speech Suppression Based on Time Series Prediction of Speech Signals Using Neural Networks
语音增强 | 5.5/10
论文解读
Navigating Speech Enhancement for Real-Time MRI: A Systematic Assessment of Signal Quality, Source Preservation, and Downstream Tasks
语音增强 | 5.7/10
论文解读
Separate First, Then Associate: A Two-Stage Approach for Real-World Audio-Visual Speech Enhancement
音视频语音分离 | 6.2/10
论文解读
HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
语音增强 | 5.9/10
论文解读
Deep Learning Based Relative Transfer Matrix Estimation for Multiple Sources and Multiple Microphones
语音增强 | 5.1/10