语音助手设备中的自适应实时语音处理方法研究  

Research on Adaptive RealTime Speech Processing Method in Voice Assistant Equipment

作　　者：晁松杰 娄艺[1] CHAO Songjie;LOU Yi(Luohe Vocational Technology College,Luohe 462000,China)

机构地区：[1]漯河职业技术学院,河南漯河462000

出　　处：《电声技术》2024年第2期42-44,共3页Audio Engineering

摘　　要：文章研究了一种基于门控循环单元(Gated Recurrent Unit,GRU)的实时语音去噪和增强方法,以优化语音助手设备的性能。介绍语音助手的基本结构,引入GRU模型作为关键组成部分,提高语音去噪和增强的效果。实验阶段采用noisex-92数据集,通过信噪比(Signal-to-Noise Ratio,SNR)增益和语音质量评估(Perceptual Evaluation of Speech Quality,PESQ)等指标对方法进行全面评估。实验结果表明,所提方法在提高语音质量和用户体验方面具备显著优势。In this paper,a real-time speech denoising and enhancement method based on Gated Recurrent Unit(GRU)is studied to optimize the performance of voice assistant devices.This section describes the structure of the voice assistant,the CRU model is introduced as a key component to improve the effect of speech denoising and enhancement.In the experimental phase,noisex-92 dataset was used to evaluate the method comprehensively by Signal-to-Noise Ratio(SNR)gain and Perceptual Evaluation of Speech Quality(PESQ).The experimental results show that the proposed method has significant advantages in improving voice quality and user experience.

关 键 词：语音助手 门控循环单元 语音去噪 语音增强 

分 类 号：TN912.2[电子电信—通信与信息系统]