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

Abstract 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.

[1]  R. Zatorre,et al.  Voice-selective areas in human auditory cortex , 2000, Nature.

[2]  M. Mills,et al.  Recognition of mother's voice in early infancy , 1974, Nature.

[3]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[4]  John D E Gabrieli,et al.  Human Voice Recognition Depends on Language Ability , 2011, Science.

[5]  John H. L. Hansen,et al.  Speaker Recognition by Machines and Humans: A tutorial review , 2015, IEEE Signal Processing Magazine.

[6]  R. Blossey.  Self-cleaning surfaces — virtual realities , 2003, Nature materials.

[7]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[8]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[9]  Robert S. Boyer,et al.  MJRTY: A Fast Majority Vote Algorithm , 1991, Automated Reasoning: Essays in Honor of Woody Bledsoe.

[10]  Suyoung Yang,et al.  Flexible highly-effective energy harvester via crystallographic and computational control of nanointerfacial morphotropic piezoelectric thin film , 2017, Nano Research.

[11]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[12]  Y. Jung,et al.  Flexible one diode-one phase change memory array enabled by block copolymer self-assembly. , 2015, ACS nano.

[13]  Hans-Günter Hirsch,et al.  Speech recognition at multiple sampling rates , 2001, INTERSPEECH.

[14]  T. Cui,et al.  Three-dimensional broadband ground-plane cloak made of metamaterials , 2010, Nature communications.

[15]  Zhong Lin Wang,et al.  Eye motion triggered self-powered mechnosensational communication system using triboelectric nanogenerator , 2017, Science Advances.

[16]  Zhaona Wang,et al.  Eardrum‐Inspired Active Sensors for Self‐Powered Cardiovascular System Characterization and Throat‐Attached Anti‐Interference Voice Recognition , 2015, Advanced materials.

[17]  Hyuk-Sang Kwon,et al.  Self-powered deep brain stimulation via a flexible PIMNT energy harvester , 2015 .

[18]  Geon-Tae Hwang,et al.  Flexible Piezoelectric Thin‐Film Energy Harvesters and Nanosensors for Biomedical Applications , 2015, Advanced healthcare materials.

[19]  Sebastian Nowozin,et al.  Image Segmentation UsingHigher-Order Correlation Clustering , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Jae Hyun Han,et al.  Basilar membrane-inspired self-powered acoustic sensor enabled by highly sensitive multi tunable frequency band , 2018, Nano Energy.

[21]  H. Wada,et al.  Piezoelectric materials mimic the function of the cochlear sensory epithelium , 2011, Proceedings of the National Academy of Sciences.

[22]  S. Priya,et al.  Laser Irradiation of Metal Oxide Films and Nanostructures: Applications and Advances , 2018, Advanced materials.

[23]  Kyungjun Song,et al.  Sound Pressure Level Gain in an Acoustic Metamaterial Cavity , 2014, Scientific Reports.

[24]  Seungjun Kim,et al.  Skin‐Like Oxide Thin‐Film Transistors for Transparent Displays , 2016 .

[25]  Chang Kyu Jeong,et al.  Highly‐Efficient, Flexible Piezoelectric PZT Thin Film Nanogenerator on Plastic Substrates , 2014, Advanced materials.

[26]  Myunghwan Byun,et al.  Flexible Crossbar‐Structured Resistive Memory Arrays on Plastic Substrates via Inorganic‐Based Laser Lift‐Off , 2014, Advanced materials.

[27]  Jr. J.P. Campbell,et al.  Speaker recognition: a tutorial , 1997, Proc. IEEE.

[28]  Chang D. Yoo,et al.  Underdetermined Convolutive BSS: Bayes Risk Minimization Based on a Mixture of Super-Gaussian Posterior Approximation , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[29]  Chang Kyu Jeong,et al.  In Vivo Self‐Powered Wireless Transmission Using Biocompatible Flexible Energy Harvesters , 2017 .

[30]  Pio G. Iovenitti,et al.  Modelling and Optimisation of a Spring-Supported Diaphragm Capacitive MEMS Microphone , 2010 .

[31]  Young-Ho Cho,et al.  A surface-micromachined capacitive microphone with improved sensitivity , 2013 .

[32]  J D Joannopoulos,et al.  Multimaterial piezoelectric fibres. , 2010, Nature materials.

[33]  Jie Chen,et al.  A highly sensitive, self-powered triboelectric auditory sensor for social robotics and hearing aids , 2018, Science Robotics.

[34]  Shin Hur,et al.  Flexible Inorganic Piezoelectric Acoustic Nanosensors for Biomimetic Artificial Hair Cells , 2014 .

[35]  Yi-Kuen Lee,et al.  Breaking the size barrier of capacitive MEMS microphones from critical length scale , 2017, 2017 19th International Conference on Solid-State Sensors, Actuators and Microsystems (TRANSDUCERS).

[36]  Rainer Goebel,et al.  "Who" Is Saying "What"? Brain-Based Decoding of Human Voice and Speech , 2008, Science.

[37]  Frank K. Soong,et al.  A Syllable Lattice Approach to Speaker Verification , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[38]  Jont B. Allen,et al.  Short term spectral analysis, synthesis, and modification by discrete Fourier transform , 1977 .

[39]  Chang Dong Yoo,et al.  Underdetermined High-Resolution DOA Estimation: A $2\rho$ th-Order Source-Signal/Noise Subspace Constrained Optimization , 2015, IEEE Transactions on Signal Processing.

[40]  R. Ruoff,et al.  Laser-induced phase separation of silicon carbide , 2016, Nature Communications.

[41]  Geon-Tae Hwang,et al.  Self‐Powered Wireless Sensor Node Enabled by an Aerosol‐Deposited PZT Flexible Energy Harvester , 2016 .

[42]  Gunter Dueck,et al.  Highly Sensitive! , 2005, Informatik-Spektrum.

[43]  Dae Yong Park,et al.  Laser–Material Interactions for Flexible Applications , 2017, Advanced materials.

[44]  David J. Ward,et al.  Artificial intelligence: Fast hands-free writing by gaze direction , 2002, Nature.