基于双微麦克风阵列与WideResNet网络的语音命令词识别  

SPEECH COMMAND WORD RECOGNITION BASED ON DUAL MICRO MICROPHONE ARRAY AND WIDE RESNET

作　　者：祁潇潇 曾庆宁[1] 赵学军 Qi Xiaoxiao;Zeng Qingning;Zhao Xuejun(School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,Guangxi,China)

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《计算机应用与软件》2024年第5期126-130,共5页Computer Applications and Software

基　　金：国家自然科学基金项目(61961009);广西自然科学基金重点项目(2016GXNSFDA380018);广西无线宽带通信与信号处理重点实验室基金项目(GXKL06200107)。

摘　　要：为了提高噪声环境下语音识别的稳健性[1],提出宽残差深度神经网络的语音识别算法。该算法结合双微麦克风阵列系统、语音数据集为双微麦克风数据集,使用功率归一化倒谱系数作为特征参数输入到残差网络中进行训练。实验表明,与ResNet15模型、ResNet18模型相比,只有三个残差模块的宽残差网络在噪声环境下语音命令词的识别和内外部说话人检测任务中具有较高的准确度,均达到了95%以上。In order to improve the robustness of speech recognition in noise environment,a speech recognition algorithm based on wide residual deep neural network is proposed.The algorithm combined the dual micro microphone array system,and the voice data set was the dual micro microphone data set.The power normalized cepstrum coefficient was used as the characteristic parameter to input into the residual network for training.Experimental results show that,compared with the Resnet15 model and Resnet18 model,the wide ResNet with only three residual modules has higher accuracy in the recognition of speech command words and the internal and external speaker detection task under noise environment,both reaching more than 95%.

关 键 词：语音识别 宽残差神经网络 功率归一化倒谱系数 双微麦克风阵列 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]