Earticle

초록

영어

The paper presents successful experiments on combining two speaker recognition methods into a hybrid system. The rst branch of recognition is an innovative approach based on discrete wavelet-Fourier transform. The second one is classic, based on HTK and classication into voice and unvoice segments. The hybrid solution outperforms both on a small test set. Further tests of this soultion will be conducted and reported.

목차

Abstract
 1 Introduction
 2 Models of voice generation
  2.1 Lungs
  2.2 Larynx
  2.3 Vocal Tract
  2.4 Source-lter model for speech production
 3 Wavelet-Fourier Transform
 4 System architecture
 5 Results
 6 Conclusions
 References

저자

• Bartosz Zio lko [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]
• Wojciech Koz lowski [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]
• Mariusz Zio lko [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]
• Rafa l Samborski [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]
• David Sierra [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]
• Jakub Ga lka [ Department of Electronics, AGH University of Science and Technology Krakow, Poland ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Hybrid Information Technology

• 간기

  격월간

• pISSN

  1738-9968

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605