Application of HMM-based Speech Recognition on Internet of Things for Smart Home System

• Main Authors: Hong-Yu You, 游宏裕
• Other Authors: Neng-Sheng Pai
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/72880867662752969440

碩士 === 國立勤益科技大學 === 電機工程系 === 103 === This study aims to develop a speech recognition-based Internet of Things (IoT) system, which is mainly divided into the two parts: voice recognition and IoT. The voice recognition can be divided into the feature extraction and recognition where the Mel-scale Frequency Cepstral Coefficients extraction speech features are used in the feature extraction and the Hidden Markov Model (HMM) is used in the recognition part to conduct the continuous speech recognition. In this paper, a website is established with the HTML5 and JavaScript on the user’s interface of the IoT to provide the recording and transmit the recorded voice to the server through the WebSocket for processing. The embedded system is used as the equipment under control and the old equipment’s ability of connecting to the IoT is provided by upgrading.