과학수사를 위한 한국인 음성 특화 자동화자식별시스템
Forensic Automatic Speaker Identification System for Korean Speakers
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, we introduce the automatic speaker identification system ‘SPO(Supreme Prosecutors Office) Verifier’. SPO Verifier is a GMM(Gaussian mixture model)-UBM(universal background model) based automatic speaker recognition system and has been developed using Korean speakers’ utterances. This system uses a channel compensation algorithm to compensate recording device characteristics. The system can give the users the ability to manage reference models with utterances from various environments to get more accurate recognition results. To evaluate the performance of SPO Verifier on Korean speakers, we compared this system with one of the most widely used commercial systems in the forensic field. The results showed that SPO Verifier shows lower EER(equal error rate) than that of the commercial system.
Abstract
In this paper, we introduce the automatic speaker identification system ‘SPO(Supreme Prosecutors Office) Verifier’. SPO Verifier is a GMM(Gaussian mixture model)-UBM(universal background model) based automatic speaker recognition system and has been developed using Korean speakers’ utterances. This system uses a channel compensation algorithm to compensate recording device characteristics. The system can give the users the ability to manage reference models with utterances from various environments to get more accurate recognition results. To evaluate the performance of SPO Verifier on Korean speakers, we compared this system with one of the most widely used commercial systems in the forensic field. The results showed that SPO Verifier shows lower EER(equal error rate) than that of the commercial system.
참고문헌 (10)
- Huang, X., "Spoken languageprocessing : a guide to theory algorithm, and systemdevelopment" (2001), Prentice Hall PTR
- Atal, B. S, "Effectiveness of linear predictioncharacteristics of the speech wave for automatic speakeridentification and verification", Journal of the Acoustical Societyof America, 55(6), pp.1304~1312 (1974)
- Viikki, O., "Cepstral domain segmentalfeature vector normalization for noise robust speechrecognition", Speech Communication, 25, pp.133~147 (1998)
- "A tutorial on principal componentsanalysis" (2002)[URL]
- Reynolds, D. A., "Robusttext-independent speaker identification using Gaussian mixturespeaker models", IEEE Trans. Speech Audio Processing, 3, pp.72~83 (1995)
- Gauvain, J. L, "Maximum a posterioriestimation for multivariate Gaussian mixture observations ofMarkov chains", IEEE Trans. Speech Audio Processing, 2, pp.291~298 (1994)
- Reynolds, D. A., "Speaker verification using adapted Gaussian mixture models", Digital Signal Processing, 10, pp.19~41 (2000)
- Rosenberg, A. E., "The use of cohort normalized scores forspeaker verification", International Conference on Speech andLanguage Processing, pp.599~602 (1992)
- "BATVOX webpage"[URL]
- "BATVOX user manual", ~ (2005)