LEARNABLE NONLINEAR COMPRESSION FOR ROBUST SPEAKER VERIFICATION

被引：2

作者：

Liu, Xuechen ^{[1
,2
]}

Sahidullah, Md ^{[2
]}

Kinnunen, Tomi ^{[1
]}

机构：

[1] Univ Eastern Finland, Sch Comp, Joensuu, Finland

[2] Univ Lorraine, INRIA, CNRS, LORIA, F-54000 Nancy, France

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2022年

关键词：

Speaker Verification; Nonlinear Compression; Multi-Regime Compression; RECOGNITION;

D O I：

10.1109/ICASSP43922.2022.9747185

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this study, we focus on nonlinear compression methods in spectral features for speaker verification based on deep neural network. We consider different kinds of channel-dependent (CD) nonlinear compression methods optimized in a data-driven manner. Our methods are based on power nonlinearities and dynamic range compression (DRC). We also propose multi-regime (MR) design on the nonlinearities, at improving robustness. Results on VoxCeleb1 and VoxMovies data demonstrate improvements brought by proposed compression methods over both the commonly-used logarithm and their static counterparts, especially for ones based on power function. While CD generalization improves performance on VoxCeleb1, MR provides more robustness on VoxMovies, with a maximum relative equal error rate reduction of 21.6%.

引用

页码：7962 / 7966

页数：5

共 50 条

[21] Robust Speaker Verification with Principal Pitch Components
Robert M. Nickel
Sachin P. Oswal
Ananth N. Iyer
International Journal of Speech Technology, 2005, 8 (4) : 323 - 339
[22] Robust speaker verification in colored noise environment
Medina, CA
Apolinario, JA
Alcaim, A
Alves, RG
CONFERENCE RECORD OF THE THIRTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 2003, : 1890 - 1893
[23] A robust speaker-adaptive and text-prompted speaker verification system
Hong, Qingyang, 1600, Springer Verlag (8833):
[24] A Robust Speaker-Adaptive and Text-Prompted Speaker Verification System
Hong, Qingyang
Wang, Sheng
Liu, Zhijian
BIOMETRIC RECOGNITION (CCBR 2014), 2014, 8833 : 385 - 393
[25] Deep Discriminative Embeddings for Duration Robust Speaker Verification
Li, Na
Tuo, Deyi
Su, Dan
Li, Zhifeng
Yu, Dong
19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2262 - 2266
[26] Short-time Gaussianization for robust speaker verification
Xiang, B
Chaudhari, UV
Navrátil, J
Ramaswamy, GN
Gopinath, RA
2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 681 - 684
[27] The usage of independent component analysis for robust speaker verification
Sentürk, A
Gürgen, FS
PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND APPLICATIONS, 2006, : 136 - +
[28] Robust Formant Features for Speaker Verification in the Lombard Effect
Kwak, Ileun
Kang, Hong-Goo
2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015, : 114 - 118
[29] DNN FEATURE COMPENSATION FOR NOISE ROBUST SPEAKER VERIFICATION
Du, Steven
Xiao, Xiong
Chng, Eng Siong
2015 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING, 2015, : 871 - 875
[30] Modified Segmental Histogram Equalization for robust speaker verification
Skosan, M
Mashao, D
PATTERN RECOGNITION LETTERS, 2006, 27 (05) : 479 - 486

← 1 2 3 4 5 →