适用于机舱环境的抗噪语音指令识别方案

A Noise-robust Speech Command Scheme for Air Cabin Environment

基于飞行器语音指令控制的应用环境,提出了一种高抗噪性的非特定人连接词语音识别方案。针对机舱噪声的频谱特性,采用了谱减法、倒谱均值归一化以及噪声模型适应技术。仿真测试表明,该方案的平均识别率在信噪比为0 dB的条件下达到92%以上。

In this paper, a highly noise -robust speech recognition scheme is proposed tbr the speech control of aircraft. According to the spectral characteristics of the aviation noise, some noise-robust technologies including spectralsub- traction, cepstrummean normalization and noise model adaption are applied. The simulation experiments show that the system can achieve a recognition accuracy of over 92% for the SNR of 0 dB.