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(wèn)題, 您可以本頁(yè)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?xún)?nèi)容
驗(yàn)證碼

一種引入幀間相關(guān)信息的HMM語(yǔ)音識(shí)別方法

趙力,  鄒采榮,  吳鎮(zhèn)揚(yáng)

趙力, 鄒采榮, 吳鎮(zhèn)揚(yáng). 一種引入幀間相關(guān)信息的HMM語(yǔ)音識(shí)別方法[J]. 電子與信息學(xué)報(bào), 2001, 23(4): 327-331.
引用本文: 趙力, 鄒采榮, 吳鎮(zhèn)揚(yáng). 一種引入幀間相關(guān)信息的HMM語(yǔ)音識(shí)別方法[J]. 電子與信息學(xué)報(bào), 2001, 23(4): 327-331.
Zhao Li, Zou Cairong, Wu Zhenyang. A METHOD OF HMM SPEECH RECOGNITION INTRODUCED INTER-FRAME CORRELATION[J]. Journal of Electronics & Information Technology, 2001, 23(4): 327-331.
Citation: Zhao Li, Zou Cairong, Wu Zhenyang. A METHOD OF HMM SPEECH RECOGNITION INTRODUCED INTER-FRAME CORRELATION[J]. Journal of Electronics & Information Technology, 2001, 23(4): 327-331.

一種引入幀間相關(guān)信息的HMM語(yǔ)音識(shí)別方法

A METHOD OF HMM SPEECH RECOGNITION INTRODUCED INTER-FRAME CORRELATION

  • 摘要: 該文提出了一種基于復(fù)數(shù)幀段輸入HMM的語(yǔ)音識(shí)別方法,它采用相繼的復(fù)數(shù)幀組成的特征參數(shù)向量作為語(yǔ)音識(shí)別HMM的輸入,能有效地在語(yǔ)音識(shí)別HMM中引入幀間相關(guān)信息。為了進(jìn)一步改善復(fù)數(shù)幀段輸入HMM的輸出概率分布函數(shù),作者還提出了用MGDF和RBF函數(shù)作為復(fù)數(shù)幀段輸入HMM的輸出概率分布函數(shù)的方法。通過(guò)對(duì)非特定人漢語(yǔ)孤立數(shù)字和連續(xù)數(shù)字語(yǔ)音識(shí)別試驗(yàn),證實(shí)了該文提出的引入幀間相關(guān)信息方法的有效性。
    Abstract: This paper applies segmental unit into HMM for speech recognition. In this model, several successive frames are combined and treated as an input vector. It expects that segmental unit input HMM would be effective to describe the inter-frame correlation information and has also proposed the MGDF and RBF to further improve output probability function. By comparing them with the traditional HMMs based on their speech recognition performance rates through the experiments of speaker-independent spoken digit (isolated/connected) recognition,the validity of the proposed appraoch could be verified.
    • HTML全文
  • V.N. Gupta, M. Lennig, P. Mermelstein, Integration of acoustic information in a large vocabulary word recognizer, ICASSP-87, Dallas, USA, 1987.2, 697-700.[2]坪香英一,ニュ-ラルネツト驅(qū)動(dòng)型HMM, IEICE, Technical Report, 1989, SP89-83, 33-41.[3]L. Deng, M. Aksmanoric, X. Sun, C. F. J. Wu, Speech recognition using hidden Markov models with polynomial regression functions as stationary states, IEEE Trans.[J]. on Speech Audio Processing.1994,(4):507-[4]C.J. Wellekens, Explicit correlation in hidden Maarkov model with optimized inter-frame dependence, ICASSP-95, Detroit, USA, 1995.1,209-212.[5]相川清明,河原英紀(jì),順向マスキングの時(shí)間周波數(shù)特性を模擬した動(dòng)的ケブストラムを用いた音韻識(shí)別,日本通信電子學(xué)會(huì)論文志(A),1993,J76-A(11),1514-1521.[6]井手和之,牧野正三,時(shí)間-周波數(shù)を用いた無(wú)聲破裂音の識(shí)別,日本音響學(xué)會(huì)論文志,1982,39(5),321-329.[7]M. Ostendorf, S. Roukos, A stochastic segment model for phoneme-based continuous speech recognition, IEEE Trans. on Acoust..[J]. Speech Signal Processing.1989,ASSP-37(12):1857-[8]T. Wakabayashi, S. Tsuruokaet, ed al., On the size and variable transformation of feature vector for handwritten character, IEICE, J76-D- Ⅱ (12), 2495-2503.[9]L. Zhao, H. Suzuki, S. Nakagawa, A comparison study of probability functions in HMMs through spoken digit recognition, IEICE, TRANS.INF and SYST., 1995, E78-D(6), 669-675.[10]S. Nakagawa, Estimation of probability density function and a posteriori probability and evaluation by vowel recognition, IEICE, Technical Report, 1992, SP92-24, 61-72.
  • 加載中
計(jì)量
  • 文章訪問(wèn)數(shù):  2112
  • HTML全文瀏覽量:  140
  • PDF下載量:  452
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  1999-06-11
  • 修回日期:  2000-04-23
  • 刊出日期:  2001-04-19

目錄

    /

    返回文章
    返回