Cough Detection System Based on ASR-HMM

In this paper, we propose a new approach to design a cough detection system based on speech-recognition algorithms. Our system is implemented with Kaldi opensource platform by Gaussian Mixture Model-based Hidden Markov Model (GMM-HMM) hybrid system through a simple Monophone training model. Also, a comparison between the Perceptual Linear Prediction (PLP) and Mel Frequency Cepstral Coefficient (MFCC) feature extraction methods is presented. Our proposed system can be used as a collection platform to collect naturally and spontaneous cough data from conversation or continuous speech. The system achieved the best performance when trained using the MFCC feature.

[1]  A. Menon.  Analysis of Feature Extraction Methods for Speech Recognition , 2017 .

[2]  S. Braman,et al.  Chronic cough as the sole presenting manifestation of bronchial asthma. , 1979, The New England journal of medicine.

[3]  Mourad Abbas,et al.  CLIASR: A Combined Automatic Speech Recognition and Language Identification System , 2020, 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET).

[4]  Abderrahim Beni Hssane,et al.  Feature extraction of some Quranic recitation using Mel-Frequency Cepstral Coeficients (MFCC) , 2016, 2016 5th International Conference on Multimedia Computing and Systems (ICMCS).

[5]  Hamidi Mohamed,et al.  Interactive Voice Response Server Voice Network Administration Using Hidden Markov Model Speech Recognition System , 2018, 2018 Second World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4).

[6]  Thierry Dutoit,et al.  Audio and Contact Microphones for Cough Detection , 2012, INTERSPEECH.

[7]  Ouissam Zealouk,et al.  Amazigh Speech Recognition Embedded System , 2020, 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET).

[8]  M. Harti,et al.  Arabic Speech Recognition System Based on CMUSphinx , 2007, 2007 International Symposium on Computational Intelligence and Intelligent Informatics.

[9]  Esther Rodríguez-Villegas,et al.  Automatic Cough Detection in Acoustic Signal using Spectral Features , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[10]  Shinya Takahashi,et al.  Cough detection in spoken dialogue system for home health care , 2004, INTERSPEECH.

[11]  James R. Glass,et al.  A complete KALDI recipe for building Arabic speech recognition systems , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[12]  Khalid Satori,et al.  Speech Coding Effect on Amazigh Alphabet Speech Recognition Performance , 2019 .

[13]  Khalid Satori,et al.  Amazigh Digits Speech Recognition System Under Noise Car Environment , 2020 .

[14]  Khalid Satori,et al.  Voice comparison between smokers and non-smokers using HMM speech recognition system , 2017, Int. J. Speech Technol..

[15]  Khalid Satori,et al.  Interactive Voice Application-Based Amazigh Speech Recognition , 2020 .

[16]  Sid-Ahmed Selouani,et al.  A Comparative Study of Different Speech Features for Arabic Phonemes Classification , 2016, 2016 European Modelling Symposium (EMS).

[17]  Khalid Satori,et al.  Amazigh digits through interactive speech recognition system in noisy environment , 2020, Int. J. Speech Technol..

[18]  H Hermansky,et al.  Perceptual linear predictive (PLP) analysis of speech. , 1990, The Journal of the Acoustical Society of America.

[19]  Darko Pekar,et al.  Large vocabulary continuous speech recognition for Serbian using the Kaldi toolkit , 2014 .

[20]  M. Lougheed,et al.  Bronchodilating effect of deep inspirations in asthma and chronic cough. , 2016, Journal of applied physiology.

[21]  M. Cloutier.  The coughing child. Etiology and treatment of a common symptom. , 1983, Postgraduate medicine.

[22]  P. K. Sahu,et al.  Automatic speech recognition based Odia system , 2015, 2015 International Conference on Microwave, Optical and Communication Engineering (ICMOCE).

[23]  Thomas R. Niesler,et al.  A Comparative Study of Features for Acoustic Cough Detection Using Deep Architectures* , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Adam Dabrowski,et al.  Acoustic Model Training, using Kaldi, for Automatic Whispery Speech Recognition , 2018, FedCSIS.

[25]  N. Yanagihara,et al.  The physical parameters of cough: the larynx in a normal single cough. , 1966, Acta oto-laryngologica.

[26]  Veton Kepuska,et al.  Arabic Speech Recognition System Based on MFCC and HMMs , 2020, Journal of Computer and Communications.

[27]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .