지연누적에 기반한 화자결정회로망이 도입된 구문독립 화자인식시스템

Text-Independent Speaker Identification System Using Speaker Decision Network Based on Delayed Summing

  • 발행 : 1998.04.01

초록

본 논문에서는 구문독립 화지인식 시스템에서 가장 중요한 역할을 하는 분류기를 두 단계로 나누어, 먼저 짧은 구간들에 대해서 각각의 화자에 속하는 정도를 계산하고, 다음에 계산된 결과들을 가지고 주어진 음성구간전체에 대해 가장 가능성이 높은 화자를 선택하는 구조를 제안한다. 첫번째 부분은 학습에 의해 스스로 조기하는 RBFN을 이용하여 구현하고 두번째 부분에서는 MAXNET과 지연합의 조합으로 화자를 결정한다. 이렇게 함으로써 지연합의 개수가 증가함에 따라 인식률이 100%가 되는 것을 모의 실험을 통하여 확인한다. 또한 본 논문에서는 음성의 프랙탈적인 특징이 화자인식에 사용될 수 있는지를 검토한다. 화자인식은 동질의 집단에서 13명의 성인만자의 목소리를 이용하여 닫힌집합(closed-set)의 경우로 모의실험을 하였고, 기존의 특징으로는 선형예측계수(LPC) 와 PC-cepstrum을 사용하였다.

In this paper, we propose a text-independent speaker identification system which has a classifier composed of two parts; to calculate the degree of likeness of each speech frame and to select the most probable speaker from the entire speech duration. The first part is realized using RBFN which is selforganized through learning and in the second part the speaker is determined using a con-tbination of MAXNET and delayed summings. And we use features from linear speech production model and features from fractal geometry. Closed-set speaker identification experiments on 13 male homogeneous speakers show that the proposed techniques can achieve the identification ratio of 100% as the number of delays increases.

키워드

참고문헌

  1. NTT Review v.7 Speaker Recognition Technology Tomoko Matsui;Sadaoki Furui
  2. Proc. ICASSP'93 Concatenated phoneme models for text-variable speaker recognition Tomoko Matsui;Sadaoki Furui
  3. Proc. IEEE v.75 Speaker Recognition Identifying People by Their Voices George R. Doddington
  4. Proc. IEEE v.64 Automatic recognition of speakers from their voices Bishnu S. Atal
  5. Proc. IEEE v.64 Automatic speaker verification : A review Aaron E. Rosenberg
  6. Proc. ICASSP'92 Free-text speaker identification over long distance telephone channel using hypothesized phonetic segmentation Yu-Hung Kao;P.K.Rajasekaran;John S. Baras
  7. IEEE Trans. on Speech and Audio Processing v.3 Robust Text Independent Speaker Identification Using Gaussian Mixture Speaker Models Douglas A. Reynolds;Richard C. Rose
  8. T&T Technical Journal v.66 A vector quantization approach to speaker recognition Frank K. Soong;Aaron E. Rosenberg;Biing Hwang Juang
  9. Automatic Speech and Speaker Recognition Voice identification using nonparametric density matching A.Higgins;L.Bahler;J.Porter
  10. Proc. ICASSP'93 Voice identification using nearest-neighbor distance measure A.L.Higgins;L.G.Bahler;J.E.Porter
  11. Proc. ICASSP'91 Text independent Talker Identification with Neural Networks Laszlo Rudasi;Stephen A. Zahorian
  12. Proc. ICASSP'91 Radial basis function networks for speaker recognition J.Oglesby;J.S.Mason
  13. Proc. ICASSP'91 On the use of TDNN extraced features information in talker identification Y.Bennani;P.Gallinari
  14. Introduction to Artificial Neural Systems Jacek M. Zurada
  15. Linear Prediction of Speech J.D.Markel;A.H.Gray,Jr.
  16. Digital Processing of Speech Signals L.R.Rabiner;R.W.Schafer
  17. Chaotic and Fractal Dynamics Francis C. Moon
  18. Fractals Jens Feder
  19. Pattern Recognition Performance evaluation for four classes of textural features P.P.Ohanian;R.C.Dubes
  20. Applications of Fractals and Chaos On the synthesis and processing of fractal signals and images Jonathan M. Blackedge
  21. Proceedings of the IEEE v.78 Networks for approximation and learning Tomaso Poggio;Federico Girosi
  22. Neural Networks Simon Haykin
  23. IEEE trans. ASSP Dynamic programming algorithm optimization for spoken word recognition Hiroaki Sakoe;Seibi Chiba