Maximum Likelihood and maximum mutual information training in gender and age recognition system

被引：0

作者：

Hubeika, Valiantsina ^{[1
]}

Szoeke, Igor ^{[1
]}

Burget, Lukas ^{[1
]}

Cernocky, Jan ^{[1
]}

机构：

[1] Brno Univ Technol, Speech FIT, Brno, Czech Republic

来源：

TEXT, SPEECH AND DIALOGUE, PROCEEDINGS | 2007年 / 4629卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Gender and age estimation based on Gaussian Mixture Models (GMM) is introduced. Telephone recordings from the Czech SpeechDat-East database are used as training and test data set. Mel-Frequency Cepstral Coefficients (MFCC) are extracted from the speech recordings. To estimate the GMMs' parameters Maximum Likelihood (ML) training is applied. Consequently these estimations are used as the baseline for Maximum Mutual Information (MMI) training. Results achieved when employing both ML and MMI training are presented and discussed.

引用

页码：496 / 501

页数：6

共 50 条

[1] Maximum mutual information training for an online neural predictive handwritten word recognition system
Garcia-Salicetti S.
Dorizzi B.
Gallinari P.
Wimmer Z.
[J]. International Journal on Document Analysis and Recognition, 2001, 4 (01) : 56 - 68
[2] Applying maximum mutual information to speech recognition
[J]. Beijing Youdian Xueyuan Xuebao, 3 (82-85):
[3] Part Recognition Based on Maximum Mutual Information
Ge Sen
Huang Dagui
[J]. PROGRESS OF MACHINING TECHNOLOGY, 2009, 407-408 : 234 - 238
[4] Part recognition based on maximum mutual information
Ge, Sen
Huang, Dagui
[J]. Key Engineering Materials, 2009, 407-408 : 234 - 238
[5] On Quantization of Log-Likelihood Ratios for Maximum Mutual Information
Bauer, Andreas Winkel
Matz, Gerald
[J]. 2015 IEEE 16TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC), 2015, : 316 - 320
[6] Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition Systems
Madikeri, Srikanth
Khonglah, Banriskhem K.
Tong, Sibo
Motlicek, Petr
Bourlard, Herve
Povey, Daniel
[J]. INTERSPEECH 2020, 2020, : 4746 - 4750
[7] On maximum mutual information speaker-adapted training
McDonough, John
Woelfel, Matthias
Stoimenov, Emilian
[J]. COMPUTER SPEECH AND LANGUAGE, 2008, 22 (02): : 130 - 147
[8] On maximum mutual information speaker-adapted training
McDonough, J
Schaaf, T
Waibel, A
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 601 - 604
[9] Mutual Information Approximation via Maximum Likelihood Estimation of Density Ratio
Suzuki, Taiji
Sugiyama, Masashi
Tanaka, Toshiyuki
[J]. 2009 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, VOLS 1- 4, 2009, : 463 - +
[10] Maximum likelihood training of the embedded HMM for face detection and recognition
Nefian, AV
Hayes, MH
[J]. 2000 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL I, PROCEEDINGS, 2000, : 33 - 36

← 1 2 3 4 5 →