Journal of University of Chinese Academy of Sciences >
A forensic automatic speaker recognition method based on improved GMM-UBM
Received date: 2012-10-22
Revised date: 2013-03-22
Online published: 2013-11-15
We improved the forensic automatic speaker recognition(FASR) system based on GMM by applying the reference database to reduce the demands of suspect's recording quantity. We established an improved FASR system based on GMM-UBM, in which a small background population is used. The proposed system was tested in the database of fixed telephone channel and mobile channel, respectively.
WANG Hua-Peng , YANG Jun , WU Ming , XU Yong . A forensic automatic speaker recognition method based on improved GMM-UBM[J]. Journal of University of Chinese Academy of Sciences, 2013 , 30(6) : 800 -805 . DOI: 10.7523/j.issn.2095-6134.2013.06.013
[1] 武宁. 复杂信道下的说话人识别技术[D]. 上海:复旦大学, 2011.
[2] Wang H P, Yang J. The fusion of forensic speaker verification systems[C]//4th International Congress on Image and Signal Processing, CISP 2011. Shanghai, China, 2011.
[3] Morrison G S. Measuring the validity and reliability of forensic likelihood-ratio systems[J]. Science & Justice, 2011, 51(3): 91-98.
[4] Rose P. Forensic voice comparison with secular shibboleths: A hybrid fused GMM-multivariate likelihood ratio-based approach using alveolo-palatal fricative cepstral spectra[C]//36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011. Prague, Czech republic, 2011.
[5] Skerrett J, Neumann C, Mateos-Garcia I. A Bayesian approach for interpreting shoemark evidence in forensic casework: accounting for wear features[J]. Forensic science international, 2011, 210(1-3): 26-30.
[6] Morrison G S. Forensic voice comparison and the paradigm shift[J]. Science & Justice, 2009, 49(4): 298-308.
[7] Meuwly D, Drygajlo A. Forensic speaker recognition based on a Bayesian framework and Gaussian mixture modelling (GMM)[C]//A Speaker Odyssey-The Speaker Recognition Workshop. 2001.
[8] Alexander A, Drygajlo A. Scoring and direct methods for the interpretation of evidence in forensic speaker recognition[C]//8th international conference on spoken language processing (ICSLP 2004). Jeju, Korea, 2004.
[9] Brummer N, Preez J du. Application-independent evaluation of speaker detection[J]. Computer Speech & Language, 2006, 20(2/3): 230-275.
/
| 〈 |
|
〉 |