一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級(jí)搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號(hào)碼
標(biāo)題
留言內(nèi)容
驗(yàn)證碼

利用CASSANDRA-I神經(jīng)計(jì)算機(jī)實(shí)現(xiàn)有限詞匯連續(xù)語音識(shí)別

顧曉東,  余道衡,  趙鶴鳴

顧曉東, 余道衡, 趙鶴鳴. 利用CASSANDRA-I神經(jīng)計(jì)算機(jī)實(shí)現(xiàn)有限詞匯連續(xù)語音識(shí)別[J]. 電子與信息學(xué)報(bào), 2002, 24(7): 987-991.
引用本文: 顧曉東, 余道衡, 趙鶴鳴. 利用CASSANDRA-I神經(jīng)計(jì)算機(jī)實(shí)現(xiàn)有限詞匯連續(xù)語音識(shí)別[J]. 電子與信息學(xué)報(bào), 2002, 24(7): 987-991.
Gu Xiaodong, Yu Daoheng, Zhao Heming. Speech recognition with limited vocabulary by using CASSANDRA-I neurocomputer[J]. Journal of Electronics & Information Technology, 2002, 24(7): 987-991.
Citation: Gu Xiaodong, Yu Daoheng, Zhao Heming. Speech recognition with limited vocabulary by using CASSANDRA-I neurocomputer[J]. Journal of Electronics & Information Technology, 2002, 24(7): 987-991.

利用CASSANDRA-I神經(jīng)計(jì)算機(jī)實(shí)現(xiàn)有限詞匯連續(xù)語音識(shí)別

Speech recognition with limited vocabulary by using CASSANDRA-I neurocomputer

  • 摘要: 該文提出并討論了如何用小型神經(jīng)計(jì)算機(jī) CASSANDRA-Ⅰ進(jìn)行有限詞匯非特定人連續(xù)語音識(shí)別的方法,同時(shí)還提出了一種新的基于關(guān)鍵詞的句法分析方法.利用 CASSANDRA-Ⅰ小型神經(jīng)計(jì)算機(jī),可滿足有限詞匯連續(xù)語音實(shí)時(shí)識(shí)別的要求;利用基于關(guān)鍵詞的句法分析,可提高有限詞匯連續(xù)語音識(shí)別的識(shí)別率與識(shí)別速度。
    Abstract: A new approach for continuous speech recognition based on neurocomputer CASS-ANDRA-I and syntactic analysis based on key words is proposed. By using CASSANDRA-I, the speed of the recognition is so rapid that recognition can be at real time. By using syntactic analysis based on key words, the performance of recognition improves greatly.
    • HTML全文
  • 王守覺,等,用神經(jīng)計(jì)算機(jī)的說話人確認(rèn)系統(tǒng)及其應(yīng)用,人工神經(jīng)網(wǎng)絡(luò)與神經(jīng)計(jì)算機(jī)應(yīng)用研討會(huì),北京,1998,7,9-13[2]R.P.lippmann, An introduction to computing with neural nets, IEEE ASSP Magazine. 1987.4(2). 4-22.[3]R.P.Lippmann, Review of neural networks for speech recognition, Neural Computation, 1989,1(1),1-38.[4]Xin .Jiang, Zhengyu Gong, Fan Sun, Huisheng Chi, A hybrid speaker recognit ion system based on the auditory path model, Proc. of WCNN93, Porland, June 1993, II5I98-601.[5]A.Waibel, et al., Phoneme recognition using time-delay networks, IEEE Trans. on ASSP. 1989,ASSP-37(12), 1888-1898.[6]俞一彪,袁保宗,連續(xù)語音識(shí)別中句法結(jié)構(gòu)知識(shí)的利用,電子學(xué)報(bào),1990,18(6),68-74[7]H. Ney, Dynamic programming parsing for context-free grammars in continuous recognition, IEEE Trans. on SP., 1991, SP-39(2), 336-340.[8]徐近霈.高枚,漢語文本讀入中音字轉(zhuǎn)換的知識(shí)集成模型和時(shí)間搜索同步算法,中文信息學(xué),1994,8(1),33-44.[9]齊士鈴,張家祿,漢語普通話輔音音長(zhǎng)分析,聲學(xué)學(xué)報(bào),1982,7(1),8-13.
  • 加載中
計(jì)量
  • 文章訪問數(shù):  2112
  • HTML全文瀏覽量:  88
  • PDF下載量:  471
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2000-10-16
  • 修回日期:  2001-02-05
  • 刊出日期:  2002-07-19

目錄

    /

    返回文章
    返回