Machine learning-based self-powered acoustic sensor for speaker recognition

被引：139

作者：

Han, Jae Hyun ^{[1
]}

Bae, Kang Min ^{[2
]}

Hong, Seong Kwang ^{[1
]}

Park, Hyunsin ^{[2
]}

Kwak, Jun-Hyuk ^{[4
]}

Wang, Hee Seung ^{[1
]}

Joe, Daniel Juhyung ^{[1
]}

Park, Jung Hwan ^{[1
]}

Jung, Young Hoon ^{[1
]}

Hur, Shin ^{[3
]}

Yoo, Chang D. ^{[2
]}

Lee, Keon Jae ^{[1
]}

机构：

[1] Korea Adv Inst Sci & Technol, Dept Mat Sci & Engn, 291 Daehak Ro, Daejeon 34141, South Korea

[2] Korea Adv Inst Sci & Technol, Dept Elect Engn, 291 Daehak Ro, Daejeon 34141, South Korea

[3] KIMM, Dept Nat Inspired Nanoconvergence Syst, 156 Gajeongbuk Ro, Daejeon 34103, South Korea

[4] CAMM, 156 Gajeongbuk Ro, Daejeon 34103, South Korea

来源：

NANO ENERGY | 2018年 / 53卷

基金：

新加坡国家研究基金会;

关键词：

Flexible piezoelectric; Self-powered; Acoustic sensor; Machine learning algorithm; Speaker recognition; HUMAN VOICE; NANOSENSORS;

D O I：

10.1016/j.nanoen.2018.09.030

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

Herein, we report a new platform of machine learning-based speaker recognition via the flexible piezoelectric acoustic sensor (f-PAS) with a highly sensitive multi-resonant frequency band. The resonant self-powered f-PAS was fabricated by mimicking the operating mechanism of the basilar membrane in the human cochlear. The f-PAS acquired abundant voice information from the multi-channel sound inputs. The standard TIDIGITS dataset were recorded by the f-PAS and converted to frequency components by using a Fast Fourier Transform (FFT) and a Short-Time Fourier Transform (STFT). The machine learning based Gaussian Mixture Model (GMM) was designed by utilizing the most highest and second highest sensitivity data among multi-channel outputs, exhibiting outstanding speaker recognition rate of 97.5% with error rate reduction of 75% compared to that of the reference MEMS microphone.

引用

页码：658 / 665

页数：8

共 43 条

[1] SHORT-TERM SPECTRAL ANALYSIS, SYNTHESIS, AND MODIFICATION BY DISCRETE FOURIER-TRANSFORM [J].

ALLEN, JB .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1977, 25 (03) :235-238

[2] Voice-selective areas in human auditory cortex [J].

Belin, P ;

Zatorre, RJ ;

Lafaille, P ;

Ahad, P ;

Pike, B .

NATURE, 2000, 403 (6767) :309-312

[3] Self-cleaning surfaces - virtual realities [J].

Blossey, R .

NATURE MATERIALS, 2003, 2 (05) :301-306

[4]

Boyer R. S., 1991, Automated Reasoning: Essays in Honor of Woody Bledsoe, P105, DOI [DOI 10.1007/978-94-011-3488-05, DOI 10.1007/978-94-011-3488-0_5]

[5] Speaker recognition: A tutorial [J].

Campbell, JP .

PROCEEDINGS OF THE IEEE, 1997, 85 (09) :1437-1462

[6] Underdetermined Convolutive BSS: Bayes Risk Minimization Based on a Mixture of Super-Gaussian Posterior Approximation [J].

Cho, Janghoon ;

Yoo, Chang D. .

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2015, 23 (05) :828-839

[7] Laser-induced phase separation of silicon carbide [J].

Choi, Insung ;

Jeong, Hu Young ;

Shin, Hyeyoung ;

Kang, Gyeongwon ;

Byun, Myunghwan ;

Kim, Hyungjun ;

Chitu, Adrian M. ;

Im, James S. ;

Ruoff, Rodney S. ;

Choi, Sung-Yool ;

Lee, Keon Jae .

NATURE COMMUNICATIONS, 2016, 7

[8] Underdetermined High-Resolution DOA Estimation: A 2ρth-Order Source-Signal/Noise Subspace Constrained Optimization [J].

Choi, Jin Ho ;

Yoo, Chang D. .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2015, 63 (07) :1858-1873

[9]

Egusa S, 2010, NAT MATER, V9, P643, DOI [10.1038/NMAT2792, 10.1038/nmat2792]

[10] Who Is Saying "What"? Brain-Based Decoding of Human Voice and Speech [J].

Formisano, Elia ;

De Martino, Federico ;

Bonte, Milene ;

Goebel, Rainer .

SCIENCE, 2008, 322 (5903) :970-973

← 1 2 3 4 5 →