近年來，隨著物聯網與深度學習的發展，人工智慧的應用更加廣泛。智慧音箱的出現改變消費者的使用習慣，能使消費者直接用口頭下達指令。這種趨勢也說明未來的家電會偏向用語音輸入指令，但多數家電的運作不像個人電腦有作業系統分配運算資源，是由多個微控制器組織重覆執行功能。要用語音指令控制微控制器，勢必要在微控制器上運行喚醒詞辨識系統。 本論文採用Depth-wise Separable Convolution來實作喚醒詞辨識模型，使用Depth-wise Separable Convolution能大幅減少參數，對於在記憶體和運算限制的微控制器有很大的幫助。此系統會先經由梅爾倒頻譜系數(MFCC)將語音資料轉成特徵，再利用類神經網路訓練，學習喚醒詞的類別，辨識特徵是否有包含喚醒詞。 ;In recent years, with the development of the IoT(Internet of Things) and deep learning, artificial intelligence has been applied in more places. The appearance of smart speakers has changed consumers’ habits and enabled them to directly give verbal instructions. This trend also shows that the future of home appliances will tend to use voice input commands, but most home appliances do not operate like the personal computer has an operating system to allocate computing resources, is organized by multiple micro- controllers to repeatedly perform functions. To control the microcontroller with voice commands, it is necessary to run a wake-up word recognition system on the micro- controller. In this thesis, we uses Depth-wise Separable Convolution to implement the wake word recognition model. Using Depth-wise Separable Convolution can greatly reduce the parameters, which is very helpful for microcontrollers with limited memory and computing. This system will first convert the voice data into features through MFCC, and then use neural network training to learn the types of wake-up words and identify whether the features contain wake-up words.
