發明
美國
13/177,608
US 8,918,319 B2
語音辨識裝置及其辨識方法SPEECH RECOGNITION DEVICE AND SPEECH RECOGNITION METHOD USING SPACE-FREQUENCY SPECTRUM
國立交通大學
2014/12/23
本發明提出了一套使用麥克風陣列偵測關鍵字的方法,本方法運用聲源於麥克風陣列在不同頻率的特徵空間一致性(Spatial Eigenspace Consistency),以及關鍵字語音共鳴曲線相似度(Resonant Curve Similarity)作為判別關鍵字的特徵,並藉由貝氏風險評估與串聯式分類器的結合做為偵測的機制。此方法在極低訊噪比下仍保有相當強健的辨識率,因而可以適用在遠距關鍵字語音偵測或者在吵雜的環境下作為關鍵字語音喚醒機制。 This invention proposes a method to detect keywords using microphone array. The consistency of the spatial eigenspaces formed by the speech source at different frequencies and the resonant curve similarity of the keyword are used as the features for detection. These features are processed and detected separately and the result is determined by cascading individual outcome using Bayes risk estimate. This proposed method can keep a high recognition rate under very low SNR conditions. Therefore, it is suitable for the applications such as distant wake-up and keyword detection in noisy environments.
本部(收文號1090020336)同意該校109年4月6日交大研產學字第1091002952號函申請終止維護專利(交大)
智慧財產權中心
03-5738251
版權所有 © 國家科學及技術委員會 National Science and Technology Council All Rights Reserved.
建議使用IE 11或以上版本瀏覽器,最佳瀏覽解析度為1024x768以上|政府網站資料開放宣告
主辦單位:國家科學及技術委員會 執行單位:台灣經濟研究院 網站維護:台灣經濟研究院