windows平台音频ai-aec高级回声消除demo

本demo主要基于深度学习的aec回声消除开发用神经网络更精确区分回声与近端语音减少误判。在线性滤波后用神经网络做精细化的残余回声抑制。从效果和性能全面超越webrtc aec3.资源链接windows平台音频ai-aec高级回声消除demo资源-CSDN下载用法AEC4 Demo - AEC4-API v1.0.0 (Advanced AEC)AEC4 Demo v1.0 - AEC4-API v1.0.0 (Advanced AEC)Usage:aec4.exe file far.wav near.wav out.wav [rate] [nlp]aec4.exe stream far.wav near.wav out.wav [rate] [nlp]aec4.exe synth out.wav [duration] [rate] [nlp]aec4.exe bench [duration] [rate] [nlp]Modes:file - Offline file processing (pre-buffer render)stream - Real-time stream simulation (interleaved render/capture)synth - Generate synthetic test signalsbench - Performance benchmarkExamples:aec4.exe file far.wav near.wav out.wav 16000 4aec4.exe stream far.wav near.wav out.wav 16000 4aec4.exe synth test.wav 10 16000 4aec4.exe bench 60 16000 4自带测试case: near_end.wav 和 far_end.wav笔记本环境测试 CPU: AMD Ryzen 5 7640HS w/ Radeon 760M Graphics (4.30 GHz)