首页|基于语音情感识别的智能照明控制系统的研究

基于语音情感识别的智能照明控制系统的研究

扫码查看
文章针对传统智能照明控制系统中因未考虑用户语音指令所蕴含的情感信息导致照明控制效果不理想的问题,提出一种将梅尔倒谱系数(Mel-Frequency Cepstral Coefficients,MFCC)特征参数与长短时记忆(Long Short-Term Memory,LSTM)网络进行融合的语音情感识别方法.通过对用户语音指令中所蕴含的情感信息进行识别,实现照明控制系统的个性化自动调节.通过搭建实验环境对改进的方案进行验证,实验结果表明,改进后的方案能够有效识别语音指令中的情感类别,满足实际使用需求.
Research on Intelligent Lighting Control System Based on Speech Emotion Recognition
Aiming at the traditional intelligent lighting control system,the problem of unsatisfactory lighting control effect due to failure to consider the emotional information contained in the user's voice commands,we propose a voice emotion recognition method that integrates the Mel-Frequency Cepstral Coefficients(MFCC)feature parameter with the Long Short-Term Memory(LSTM)network,and realizes the personalized automatic adjustment of the lighting control system by recognizing the emotional information contained in the user's voice commands,and then finally,we set up an experimental environment to validate the improved scheme.Finally,the improved scheme is verified by building an experimental environment,and the experimental results show that the improved scheme can effectively recognize the emotion categories in the voice commands and meet the practical use requirements.

speech emotion recognitionsmart lightingLong Short-Term Memory(LSTM)network

王晓康

展开 >

江苏亚明照明有限公司,江苏 盐城 224700

语音情感识别 智能照明 长短时记忆(LSTM)网络

2024

电声技术
电视电声研究所(中国电子科技集团公司第三研究所)

电声技术

影响因子:0.259
ISSN:1002-8684
年,卷(期):2024.48(2)
  • 10