基于隐马尔可夫模型的语音识别技术在载人航天器上的应用

利用嵌入式平台构建了基于隐马尔可夫模型(Hidden Markov Model,HMM)技术的载人航天器语音识别系统,并针对载人航天器特殊的噪声背景和声学训练,对传统语音端点检测算法进行了改进。通过试验在嵌入式运行环境下实现了指令发送、文字输入等功能,证实该系统适应航天员的口音和发音习惯,可对连贯自然发音方式的命令进行识别,能够满足航天员及任务使用需求。

Spacecraft speech recognition based on Hidden Markov Model (HMM) technology

This paper reviews the theory of the Hidden Markov Model （HMM） and the speech recognition system. By using the embedded platform, the manned -spacecraft speech recognition system is built based on the HMM technology. To meet complex requirements of future spacecraft for speech recognition, the specifications and rules for the speech recognition are optimized, with an improvement of the accuracy rate over the traditional voice activity detection algorithm. The application of this continuous speech recognition system on manned-spacecraft shows good results for the function implementation of command sending and character input.