利用國語411音節間之混淆量測設計之關鍵詞辨認方法

Abstract

本論文中，對以411音節為填充模型的關鍵詞辨認進行改良，研究的主題在於 411音節間混淆程度的量測。由411音辨認分數之機率分佈定義出混淆懲罰量，並將之應用在以411音為填充模型的關鍵詞辨認，得到了新的關鍵詞辨認架構。同時也加入聲調辨認，求得五個聲調間的混淆懲罰量，一併用於關鍵詞辨認上。經由電話語音測試，新的方法可將單一關鍵詞辨認的辨認率由 71.55% 提升到 75.34%，多關鍵詞辨認的辨認率由 72.76% 提升到 75.00%。在加入聲調辨認之後，單一關鍵詞的辨認率可達 80.86%，而多關鍵詞的辨認率達 79.65%。

In this thesis, a new keyword spotting method using confusion measure was proposed. The confusion measure of 411 monosyllables was first found from the pdf of recognition score of each models. By proper chosen the missing error probability, the confusion penalties could be found in monosyllable recognizer. Confusion penalties are applied to the keyword spotting system and the recognition rate of keyword recognition system is improved. Furthermore, tone recognizer is added in keyword spotting system. And, the confusion penalties of 5 tones are also applied to the keyword spotting system. Performance of the proposed method is examined by simulations using real telephone-speech database. The new method improves the recognition rate of one-keyword system from 71.55% to 75.34% and that of multi-keyword system from 72.76% to 75.00%. With tone recognition, the recognition rate of 80.86% for one-keyword system and 79.65% for multi-keyword system are achieved.