基于DTW的語音關(guān)鍵詞檢出
發(fā)布時(shí)間:2018-07-24 19:03
【摘要】:針對(duì)少資源語言的語音關(guān)鍵詞檢出技術(shù)受到了廣泛關(guān)注。該文在基于動(dòng)態(tài)時(shí)間規(guī)整(dynamic time warping,DTW)的關(guān)鍵詞檢出框架下,提出了基于音素邊界的局部匹配策略,用以解決基于樣例的語音關(guān)鍵詞檢出任務(wù)中的近似查詢問題。在QUESST 2014評(píng)測數(shù)據(jù)上采用多種特征進(jìn)行了實(shí)驗(yàn)驗(yàn)證。實(shí)驗(yàn)結(jié)果顯示:基于音素邊界的局部匹配策略不僅在近似查詢T2和T3任務(wù)上的檢出效果明顯提升,在精確查詢T1任務(wù)上也獲得了有效提升。隨后的系統(tǒng)融合實(shí)驗(yàn)表明,該策略能夠大幅提升融合系統(tǒng)的性能。
[Abstract]:Speech keyword detection technology for less resource languages has been paid more and more attention. In this paper, a local matching strategy based on phoneme boundary is proposed under the framework of keyword detection based on dynamic time warping (dynamic time (dynamic time warping (dynamic time), which is used to solve the approximate query problem in speech keyword detection task based on sample. A variety of features are used to verify the QUESST 2014 data. The experimental results show that the local matching strategy based on phoneme boundary not only improves the detection effect on approximate T _ 2 and T _ 3 tasks, but also improves the precision query T _ 1 tasks. Subsequent system fusion experiments show that the strategy can greatly improve the performance of the fusion system.
【作者單位】: 西北工業(yè)大學(xué)計(jì)算機(jī)學(xué)院 陜西省語音與圖像信息處理重點(diǎn)實(shí)驗(yàn)室;南洋理工大學(xué)Temasek實(shí)驗(yàn)室;新加坡科技局資訊通信研究院 人類語言技術(shù)部;南洋理工大學(xué)計(jì)算機(jī)工程學(xué)院;
【基金】:國家自然科學(xué)基金面上項(xiàng)目(61571363)
【分類號(hào)】:TP391.3
本文編號(hào):2142341
[Abstract]:Speech keyword detection technology for less resource languages has been paid more and more attention. In this paper, a local matching strategy based on phoneme boundary is proposed under the framework of keyword detection based on dynamic time warping (dynamic time (dynamic time warping (dynamic time), which is used to solve the approximate query problem in speech keyword detection task based on sample. A variety of features are used to verify the QUESST 2014 data. The experimental results show that the local matching strategy based on phoneme boundary not only improves the detection effect on approximate T _ 2 and T _ 3 tasks, but also improves the precision query T _ 1 tasks. Subsequent system fusion experiments show that the strategy can greatly improve the performance of the fusion system.
【作者單位】: 西北工業(yè)大學(xué)計(jì)算機(jī)學(xué)院 陜西省語音與圖像信息處理重點(diǎn)實(shí)驗(yàn)室;南洋理工大學(xué)Temasek實(shí)驗(yàn)室;新加坡科技局資訊通信研究院 人類語言技術(shù)部;南洋理工大學(xué)計(jì)算機(jī)工程學(xué)院;
【基金】:國家自然科學(xué)基金面上項(xiàng)目(61571363)
【分類號(hào)】:TP391.3
【相似文獻(xiàn)】
相關(guān)重要報(bào)紙文章 前2條
1 葉向榮 鄭民軍;大破語音關(guān)[N];中國教育報(bào);2001年
2 山東省陽信縣翟王鎮(zhèn)韓箔中心小學(xué) 張玉蘭;語文課堂 讓學(xué)生快樂表達(dá)[N];學(xué)知報(bào);2010年
相關(guān)碩士學(xué)位論文 前1條
1 朱林;語音關(guān)鍵詞檢測若干問題研究[D];北京郵電大學(xué);2015年
,本文編號(hào):2142341
本文鏈接:http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2142341.html
最近更新
教材專著