Papers

Robust formant features for speaker verification in the lombard effect

International Conference
2011~2015
작성자
한혜원
작성일
2015-12-01 00:50
조회
2594
Authors : Il-eun Kwak, Hong-Goo Kang

Year : 2015

Publisher / Conference : APSIPA

Page : 114-118

This paper presents a voice controlled speaker verification system for hand-held devices in noisy environments. In noisy environments, users unintentionally increase their voice intensity because of the ear-mouth feedback mechanism i.e., the Lombard effect; thus, the characteristic of the input signal is much different from that in a quiet environment. To enhance the accuracy of a speaker verification system, this paper proposes a robust formant feature that represents the physical nature of the voice production system of the speaker. It utilizes the analysis results that the impact of Lombard varies depending on the types and levels of the background noise, but the third and fourth formant frequencies are insensitive even in the Lombard condition. Experimental results show that optimal performance can be achieved when the above formant frequencies and corresponding bandwidths are combined.
전체 365
28 International Conference Il-eun Kwak, Hong-Goo Kang "Robust formant features for speaker verification in the lombard effect" in APSIPA, pp.114-118, 2015
27 International Conference Hyeonjoo Kang, JeeSok Lee, Soonho Baek, Hong-Goo Kang "Systematic Integration of Acoustic Echo Canceller and Noise Reduction Modules for Voice Communication Systems" in INTERSPEECH, 2015
26 International Conference Kyungguen Byun, Eunwoo Song, Hong-goo Kang "A constrained two-layer compression technique for ECG waves" in Enegineering in Medicine and Biology Society (EMBC), 2015
25 International Conference Eunwoo Song, Hong-Goo Kang "Deep Neural Network-Based Statistical Parametric Speech Synthesis System Using Improved Time-Frequency Trajectory Excitation Mo" in INTERSPEECH, 2015
24 International Conference Heejin Ahn, Eunwoo Song, Won-Suk Jun, Hong-goo Kang "A Compression Algorithms for Hidden Markov Model-Based Speech Synthesis Systems" in ITC-CSCC, pp.942-945, 2015
23 International Conference JeeSok Lee, Sejin Oh, Hong-Goo Kang "Coherent channel based subband multichannel dereverberation" in ICASSP, pp.2704-2708, 2015
22 International Conference Eunwoo Song, Young-Sun Joo, Hong-Goo Kang "Improved time-frequency trajectory excitation modeling for a statistical parametric speech synthesis system" in ICASSP, 2015
21 International Conference Eunwoo Song, Hong-Goo Kang, Joonil Lee "Fixed-point implementation of MPEG-D unified speech and audio coding decoder" in 19th International Conference on Digital Signal Processing (DSP), pp.110-113, 2014
20 International Conference Soonho Baek, Hong-Goo Kang "Mean normalization of power function based cepstral coefficients for robust speech recognition in noisy environment" in ICASSP, 2014
19 International Conference Ho Seon Shin, Hong-Goo Kang "Bone-Conduction Speech Enhancement using a Speaker-Independent Filter" in ICEIC, 2014