\ COMBINING REGRESSION AND CLASSIFICATION METHODS FOR IMPROVING AUTOMATIC SPEAKER AGE RECOGNITION

被引：21
|
作者：
van Heerden, Charl [1 ]
Barnard, Etienne [1 ]
Davel, Marelie [1 ]
van der Walt, Christiaan [1 ]
van Dyk, Ewald [1 ,2 ]
Feld, Michael [2 ]
Mueller, Christian [2 ]
机构：
[1] CSIR, Human Language Technol Meraka Inst, Pretoria, South Africa
[2] German Res Ctr AI, Intrlligent User Interface, Berlin, Germany
来源：
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年
关键词：
Age classification; gender classification; support vector machines;
D O I：
10.1109/ICASSP.2010.5495006
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
We present a novel approach to automatic speaker age classification, which combines regression and classification to achieve competitive classification accuracy on telephone speech. Support vector machine regression is used to generate finer age estimates, which are combined with the posterior probabilities of well-trained discriminative gender classifiers to predict both the age and gender of a speaker. We show that this combination performs better than direct 7-class classifiers. The regressors and classifiers are trained using long-term features such as pitch and formants, as well as short-term (frame-based) features derived from MAP adaptation of GMMs that were trained on MFCCs.
引用
收藏
页码：5174 / 5177
页数：4
相关论文
共 50 条
  • [1] Combining Five Acoustic Level Modeling Methods for Automatic Speaker Age and Gender Recognition
    Li, Ming
    Jung, Chi-Sang
    Han, Kyu J.
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2830 - +
  • [2] Classification methods for speaker recognition
    Massachusetts Institute of Technology, Lincoln Laboratory, 244 Wood Street, Lexington, MA 02420, United States
    Lect. Notes Comput. Sci., 2007, (278-297):
  • [3] Automatic Classification of Marine Mammals with Speaker Classification Methods
    Kreimeyer, Roman
    Ludwig, Stefan
    EFFECTS OF NOISE ON AQUATIC LIFE II, 2016, 875 : 573 - 581
  • [4] Combining regression and classification methods for age band estimation from human faces
    Yannick, Lufimpu-Luviya
    Sebastien, Paris
    Djamel, Merad
    Bernard, Fertil
    2013 8TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS (ISPA), 2013, : 136 - 141
  • [5] COMBINING SPEAKER AND NOISE FEATURE NORMALIZATION TECHNIQUES FOR AUTOMATIC SPEECH RECOGNITION
    Garcia, L.
    Benitez, C.
    Segura, J. C.
    Umesh, S.
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5496 - 5499
  • [6] SPEAKER-ADAPTABLE CLASSIFICATION PROCEDURE FOR AUTOMATIC SPEECH RECOGNITION
    KATTERFELDT, H
    THON, W
    NACHRICHTENTECHNISCHE ZEITSCHRIFT, 1974, 27 (06): : 230 - 232
  • [7] Combining Short-term Cepstral and Long-term Pitch Features for Automatic Recognition of Speaker Age
    Mueller, Christian
    Burkhardt, Felix
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2268 - +
  • [8] Multilingual Speaker Age Recognition: Regression Analyses on the Lwazi Corpus
    Feld, Michael
    Barnard, Etienne
    van Heerden, Charl
    Mueller, Christian
    2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 534 - 539
  • [9] Automatic speaker recognition
    Moon, M. M.
    Cheeran, Alice
    PROCEEDINGS OF THE FOURTH IASTED INTERNATIONAL CONFERENCE ON CIRCUITS, SIGNALS, AND SYSTEMS, 2006, : 287 - +
  • [10] Speaker age classification and regression using i-vectors
    Grzybowska, Joanna
    Kacprzak, Stanislaw
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1402 - 1406
12345