嵌入式語音偵測與關鍵詞辨識系統

Abstract

在本論文中，我們將Isolated word辨識與Keyword spotting分別實現於嵌入式平台環境。在Isolated word辨識中，系統目標為建立辨識詞庫一千詞彙的Embedded Automatic Speech Recognition (eASR)系統。在辨識速度上小於兩倍語音輸入時間，以及辨識率在乾淨環境中超過95%，而在車環境下超過90%，為了加速辨識以及使用上的便利性，我們加入語音偵測技術，然而在嵌入式系統中，為了解決電容式麥克風在充電時輸出的不可靠，我們並非以開始為語音訂定臨界值(threshold)，而是採用適應性臨界值。在Keyword spotting中，我們使用與關鍵詞聲學模型一樣的填充模型，並考慮以關鍵詞長挑選最佳路徑，其辨識率在乾淨環境中超過90%。

In this thesis, an embedded isolated Mandarin word recognition system and keyword spotting were implemented in a Windows-CE based mobile device. The speech recognition system used a HMM recognizer using partition Lapalacian observation probability. The system was carefully tuning in order to get the near real-time response without performance degeneration. Finally, the isolated Mandarin word recognition system, the system response time is about 1.2 times real time and 95.8% word recognition rate can be achieved for a 1000 words application, in the other hand, keyword spotting response time is 1.8 real time and 91.6% recognition rate for a 776 words.