Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 胡竹生 | en_US |
dc.contributor.author | 李明唐 | en_US |
dc.contributor.author | 王庭昭 | en_US |
dc.contributor.author | 楊佳興 | en_US |
dc.date.accessioned | 2014-12-16T06:12:01Z | - |
dc.date.available | 2014-12-16T06:12:01Z | - |
dc.date.issued | 2012-12-16 | en_US |
dc.identifier.govdoc | G10L015/02 | zh_TW |
dc.identifier.uri | http://hdl.handle.net/11536/103345 | - |
dc.description.abstract | 本發明係揭露一種語音辨識裝置及其語音辨識方法,其係接收至少一關鍵詞以進行辨識,此關鍵詞包括至少一關鍵字。首先,接收關鍵字之一聲源訊號,以產生複數聲音訊號,進而將其轉換至頻域,形成複數聲頻訊號。接著,藉聲頻訊號擷取出一空間頻譜及其角度估測値。再來,利用空間頻譜定義至少一空間特徵參數輸出之,並依據角度估測値與聲頻訊號進行擷取與評估,輸出一巴塔恰里雅距離。最後,接收上述特徵與距離,以利用與其對應之檢測門檻値判斷關鍵詞之正確性,如此便可在極低訊噪比之環境下,仍達成相當强健的語音辨識率。 | zh_TW |
dc.language.iso | zh_TW | en_US |
dc.title | 語音辨識裝置及其辨識方法 | zh_TW |
dc.type | Patents | en_US |
dc.citation.patentcountry | TWN | zh_TW |
dc.citation.patentnumber | 201250670 | zh_TW |
Appears in Collections: | Patents |
Files in This Item:
If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.