近幾年來，嵌入式系統的技術及產品已成為全球IT產業的重點之一。此論文研討音訊的定位與增强於嵌入式系統的實現，所嵌入的演算法有方位偵測與混合音源分離。這兩種演算法分別用不同的嵌入式系統來實現，方位偵測使用TI TMS320C6713 DSK做開發，混合音源分離使用Raspberry Pi 2來開發。實驗部分，方位偵測測出的角度達到不錯效果，誤差皆在10度以內；混合音源分離，實驗一使用SIR來評估，1m與2m的平均SIR爲16.72與15.76，實驗二使用語音辨識來評估，此演算法使語音辨識提高至95%。
;In recent years, the technology and products of embedded system has become one of the focus of the global IT industry. In this paper, we proposed sound localization and enhancement on embedded system implementation. Sound Localization and Blind Source Separation (BSS) are embedded in embedded system. These two kinds of algorithm with different embedded system to achieve. Source Localization using TI TMS320C6713 DSK do develop, and Blind Source Separation using Raspberry Pi 2 do develop. About of experiment, Sound Localization measured errors angle are less than 10 degrees; Blind Source Separation, first experiment using SIR to evaluate, average SIR of 1m and 2m are 16.72 and 15.76 respectively. Second experiment using Speech recognition to evaluate, this algorithm to make speech recognition increased to 95%。
