摘要
基于视频的监控系统存在很多不足,声学场景识别系统依据基于人耳听觉仿生的目标声音识别技术,积极探索先进的人耳仿生理论、特征提取技术、目标声音分类技术,实现对声音场景进行自动化分类和信息抽取,具有广泛的应用前景。
As video monitoring systems has many deficiencies, Acoustic Scene Recognition System is built on target voice recognition technology based on Bionic ear hearing, and actively explore advanced ear bionic theory, feature extraction, target sound classification technology. It can achieve the sound scene automated classification and information extraction, and has broad application prospects.
出处
《数字通信世界》
2016年第7期12-14,共3页
Digital Communication World
关键词
声音识别
声音场景
特征提取
神经网络
Voice Recognitio
Sound Scene
Feature Extraction
Neural Networks
