Papers

Selecting Feature Frames for Automatic Speaker Recognition Using Mutual Information

International Journal
2006~2010
작성자
이진영
작성일
2010-08-01 14:25
조회
2376
Authors : Chi-Sang Jung, Moo Young Kim, Hong-Goo Kang

Year : 2010

Publisher / Conference : IEEE Transactions on Audio, Speech, and Language Processing

Volume : 18, issue 6

Page : 1332-1340

In this paper, an information theoretic approach to selecting feature frames for speaker recognition systems is proposed. A conventional approach in which the frame shift is fixed to around half of the frame length may not be the best choice, because the characteristics of the speech signal may rapidly change, especially at phonetic boundaries. Experimental results show that the recognition accuracy increases if the frame interval is directly controlled using phonetic information. By applying these results to the well-known fact that the recognition accuracy is directly correlated with the amount of mutual information, this paper suggests a novel feature frame selection method for speaker recognition. Specifically, feature frames are chosen to have minimum-redundancy within selected feature frames, but maximum-relevancy to speaker models. It is verified by experiments that the proposed method produces consistent improvement, especially in a speaker verification system. It is also robust against variations in acoustic environment.
전체 365
165 Domestic Journal 오현오, 정양원 "객체 오디오 부호화 표준 SAOC 기술 및 응용" in 전자공학회논문지, vol.47 SP, 제 5호, pp.45-55, 2010
164 Domestic Conference 서현선, 정치상, 강홍구 "음소 특성 기반 스코어의 퓨전 방식을 이용한 서포트 벡터 머신 기반 화자 검증 시스템" in 한국음향학회, 2010
163 Domestic Conference 신호선, 최가원, 강홍구 "잡음 환경에서의 SNR 회복 기법을 적용한 음성 향상 알고리즘을 이용한 감정인식" in 음성통신 및 신호처리학술대회, vol.27, no. 1, 2010
162 International Journal Min-Seok Choi, Hong-Goo Kang "A Two-channel Noise Estimator for Speech Enhancement in Highly Non-stationary Environment" in IEEE Transactions on Audio, Speech, and Language Processing, vol.19, issue 4, pp.905-915, 2011
161 International Journal Chi-Sang Jung, Moo Young Kim, Hong-Goo Kang "Selecting Feature Frames for Automatic Speaker Recognition Using Mutual Information" in IEEE Transactions on Audio, Speech, and Language Processing, vol.18, issue 6, pp.1332-1340, 2010
160 Domestic Journal Myung-Suk Song, Chang-Heon Lee, Seok-Pil Lee, Hong-Goo Kang "Performance Analysis of a Class of Single Channel Speech Enhancement Algorithms for Automatic Speech Recognition" in 한국음향학회지, vol.29, 제 2호, pp.86-99, 2010
159 International Conference Myung-Suk Song , Cha Zhang, Dinei Florencio, Hong-Goo Kang "Personal 3D audio system with loudspeakers" in ICME, 2010
158 Domestic Journal 정재웅, 박영철, 윤대희, 이석필 "주파수 워핑된 공통 극점을 이용한 음향 간섭제거기의 설계 및 구현" in 한국음향학회지, vol.29, 제 5호, pp.339-346, 2010
157 Domestic Conference 백순호,양재모,이석필,강홍구 "주파수 밴드 별 엔트로피 변화에 따른 잔향제거 기술" in 한국통신학회, 2010
156 Domestic Conference 전세운,박영철,이석필,윤대희 "방향 정보에 따른 가변적인 채널 게인 제어를 통한 다채널 벡터 기반의 사운드 패닝 기술에 관한 연구" in 한국통신학회, 2010