Multi-channel Convolutional Neural Networks for Automatic Detection of Speech Deficits in Cochlear Implant Users

被引：2

作者：

Arias-Vergara, Tomas ^{[1
,2
,3
]}

Vasquez-Correa, Juan Camilo ^{[1
,2
]}

Gollwitzer, Sandra ^{[3
]}

Orozco-Arroyave, Juan Rafael ^{[1
,2
]}

Schuster, Maria ^{[3
]}

Noeth, Elmar ^{[2
]}

机构：

[1] Univ Antioquia UdeA, Fac Engn, Calle 70 52-21, Medellin, Colombia

[2] Friedrich Alexander Univ, Pattern Recognit Lab, Erlangen, Germany

[3] Ludwig Maximilians Univ Munchen, Dept Otorhinolaryngol Head & Neck Surg, Munich, Germany

来源：

PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS (CIARP 2019) | 2019年 / 11896卷

基金：

欧盟地平线“2020”;

关键词：

Speech processing; Time-frequency analysis; Multi-channel CNN; Deep learning; Cochlear Implants; FEATURES;

D O I：

10.1007/978-3-030-33904-3_64

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes a methodology for automatic detection of speech disorders in Cochlear Implant users by implementing a multi-channel Convolutional Neural Network. The model is fed with a 2-channel input which consists of two spectrograms computed from the speech signals using Mel-scaled and Gammatone filter banks. Speech recordings of 107 cochlear implant users (aged between 18 and 89 years old) and 94 healthy controls (aged between 20 and 64 years old) are considered for the tests. According to the results, using 2-channel spectrograms improves the performance of the classifier for automatic detection of speech impairments in Cochlear Implant users.

引用

页码：679 / 687

页数：9

共 14 条

[1] Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users [J].

Arias-Vergara, T. ;

Orozco-Arroyave, J. R. ;

Gollwitzer, S. ;

Schuster, M. ;

Noeth, E. .

TEXT, SPEECH, AND DIALOGUE (TSD 2019), 2019, 11697 :299-306

[2]

Boski M, 2017, 2017 10TH INTERNATIONAL WORKSHOP ON MULTIDIMENSIONAL (ND) SYSTEMS (NDS)

[3]

Hudgins C.V., 1942, GENET PSYCHOL MONOGR, P289

[4]

Huerta J.M., 1998, P ICSLP, P1463

[5]

Kingma DP, 2014, ARXIV

[6]

Nakashika T, 2014, INT CONF SIGN PROCES, P505, DOI 10.1109/ICOSP.2014.7015056

[7]

Orozco-Arroyave J. R., 2016, Analysis of Speech of People With Parkinson's Disease, V41

[8]

PATTERSON RD, 1992, ADV BIOSCI, V83, P429

[9]

Pedregosa F, 2011, J MACH LEARN RES, V12, P2825

[10] Speech Production Quality of Cochlear Implant Users with Respect to Duration and Onset of Hearing Loss [J].

Ruff, Suzan ;

Bocklet, Tobias ;

Noeth, Elmar ;

Mueller, Joachim ;

Hoster, Eva ;

Schuster, Maria .

ORL-JOURNAL FOR OTO-RHINO-LARYNGOLOGY HEAD AND NECK SURGERY, 2017, 79 (05) :282-294

← 1 2 →