Amazigh digits through interactive speech recognition system in noisy environment

This paper describes the performance of Amazigh speech recognition via an interactive voice response in noisy conditions. The experiments were first conducted for the uncoded speech and then repeated for decoded speech in a noisy environment for different signal noise ratios (SNR). In this study, we analyze the effect of noise at different SNR levels on the ten first Amazigh digits which have collected from 22 Moroccan native speakers including both males and females. Our experiments results show that the degradation of accuracy was observed for all studied words by different degrees due to word components or the speech coding.

[1]  Douglas D. O'Shaughnessy,et al.  Speech enhancement using PCA and variance of the reconstruction error in distributed speech recognition , 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

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

[3]  Sheela Ganesh Thorenoor,et al.  Analysis of IP Network for different Quality of Service , 2011 .

[4]  Brian Kingsbury,et al.  New types of deep neural network learning for speech recognition and related applications: an overview , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Salem Chaker,et al.  Textes en linguistique berbère : introduction au domaine berbère , 1984 .

[6]  Alex Acero,et al.  Spoken Language Processing: A Guide to Theory, Algorithm and System Development , 2001 .

[7]  Fotini-Niovi Pavlidou,et al.  VoIP: A comprehensive survey on a promising technology , 2009, Comput. Networks.

[8]  Yifan Gong,et al.  An Overview of Noise-Robust Automatic Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[9]  Mahua Bhattacharya,et al.  ASR System Integration with Asterisk for SIP or IAX Softphone Clients , 2009, 2009 International Association of Computer Science and Information Technology - Spring Conference.

[10]  Khalid Satori,et al.  Vocal parameters analysis of smoker using Amazigh language , 2018, Int. J. Speech Technol..

[11]  James R. Glass,et al.  Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[12]  O.O. Khalifa,et al.  Human computer interaction using isolated-words speech recognition technology , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[13]  Syed Ayaz Ali Shah.  Neural Network Solution for Secure Interactive Voice Response , 2009 .

[14]  Khalid Satori,et al.  Voice pathology assessment based on automatic speech recognition using Amazigh digits , 2018, ICSDE'18.

[15]  Omar Ouakrim,et al.  Fonética y fonología del bereber , 1995 .

[16]  Vishal Passricha,et al.  Convolutional Neural Networks for Raw Speech Recognition , 2018, From Natural to Artificial Intelligence - Algorithms and Applications.

[17]  Yifan Gong,et al.  Speech recognition in noisy environments: A survey , 1995, Speech Commun..

[18]  Khalid Satori,et al.  Speech Recognition for Moroccan Dialects: Feature Extraction and Classification Methods , 2019 .

[19]  Khalid Satori,et al.  Amazigh digits speech recognition on IVR server , 2016 .

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

[21]  José A. R. Fonollosa,et al.  Automatic Speech Recognition with Deep Neural Networks for Impaired Speech , 2016, IberSPEECH.

[22]  John H. L. Hansen,et al.  CU-Move: Advanced In-Vehicle Speech Systems for Route Navigation , 2005 .

[23]  Jean-Claude Junqua,et al.  Robustness in Automatic Speech Recognition: Fundamentals and Applications , 1995 .

[24]  Fatima El Haoussi,et al.  Investigation Amazigh speech recognition using CMU tools , 2014, Int. J. Speech Technol..

[25]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[26]  Muhammad Ghulam,et al.  Speaker recognition based on Arabic phonemes , 2017, Speech Commun..

[27]  Petr Fousek,et al.  Additive noise and channel distortion-robust parametrization tool - performance evaluation on Aurora 2 & 3 , 2003, INTERSPEECH.

[28]  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).

[29]  Hong Kook Kim,et al.  Cepstrum-domain acoustic feature compensation based on decomposition of speech and noise for ASR in noisy environments , 2001, IEEE Trans. Speech Audio Process..

[30]  Vlado Delic,et al.  Deep Neural Network Based Continuous Speech Recognition for Serbian Using the Kaldi Toolkit , 2015, SPECOM.

[31]  Douglas D. O'Shaughnessy,et al.  Real-life speech-enabled system to enhance interaction with rfid networks in noisy environments , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Mohamed Salim Bouhlel,et al.  Using geometric spectral subtraction approach for feature extraction for DSR front-end Arabic system , 2017, Int. J. Speech Technol..