A neural-wavelet architecture for voice conversion

被引：19
作者：
Guido, Rodrigo Capobianco
Vieira, Lucimar Sasso
Barbon Junior, Sylvio
Sanchez, Fabricio Lopes
Maciel, Carlos Dias
Fonseca, Everthon Silva
Pereira, Jose Carlos
机构：
[1] Univ Sao Paulo, Inst Phys Sao Carlos, Dept Phys & Informat, Speech Lab FFI IFSC, BR-13560970 Sao Carlos, SP, Brazil
[2] Univ Sao Paulo, Sch Engn Sao Carlos, Dept Elect Engn, SEL EESC, BR-13560970 Sao Carlos, SP, Brazil
来源：
NEUROCOMPUTING | 2007年 / 71卷 / 1-3期
基金：
巴西圣保罗研究基金会;
关键词：
RBF neural networks; wavelet transforms; voice conversion;
D O I：
10.1016/j.neucom.2007.08.010
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this letter we propose a new architecture for voice conversion that is based on a joint neural-wavelet approach. We also examine the characteristics of many wavelet families and determine the one that best matches the requirements of the proposed system. The conclusions presented in theory are confirmed in practice with utterances extracted from TIMIT speech corpus. (c) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码：174 / 180
页数：7
相关论文
共 18 条
[1]  
ABE M, 1988, P ICASSP, V1, P655
[2]  
Addison P.S., 2002, ILLUSTRATED WAVELET, V1st ed.
[3]  
[Anonymous], 2001, NEURAL NETWORKS COMP
[4]  
Bosi M., 2012, Introduction to digital audio coding and standards
[5]  
Deng L., 2003, Speech processing: a dynamic and optimizationoriented approach
[6]  
DRIOLI C, 2001, EURASIP J APPL SIG P, P36
[7]   RESEARCH ON INDIVIDUALITY FEATURES IN SPEECH WAVES AND AUTOMATIC SPEAKER RECOGNITION TECHNIQUES [J].
FURUI, S .
SPEECH COMMUNICATION, 1986, 5 (02) :183-197
[8]  
Guido RC, 2006, CONF REC ASILOMAR C, P2115
[9]  
HAYKIN S, 1999, ADAPTIVE FILTER THEO
[10]  
JENSEN A, 2000, RIPPLES MATH DISCRET
12