Enhancement of speech corrupted by broadband noise is subject of interest in many applications. For several years, the investigation of methods of denoising the vocal signal has yielded very satisfactory results, but certain problems and questions still remain. The term speech quality in speech enhancement is associated with clarity and intelligibility. So, one of these issues is to reach a compromise between noise reduction, signal distortion and musical noise. In this paper, we studied one of the classical techniques based on the spectral subtraction developed by Boll and improved by Berouti where two parameters α and β to control the effects of the distortion and the musical noise are introduced. However, the choice on these parameters (α and β) remains empirical. Our works is to find a compromise between these two parameters to obtain an optimal solution depending on the environment, the unknown noise and its level. Moreover, we propose in this paper, an algorithm based on bi-objective approach precisely Particle Swarm Optimization (PSO) technique in association with speech enhancement technique proposed by Berouti et al. Comparative results show that the performance of our proposed method with several types of noise, depending on the environment and on various noise levels, are better than those of spectral subtraction methods of Boll or Berouti.
Mots-clés : Speech enhancement, spectral subtraction, multiobjective optimization, meta-heuristic, PSO
@article{RO_2020__54_6_1555_0, author = {Ouznadji, Said and Chaabane, Djamal and Thameri, Messaoud}, title = {Multiple objective optimization {Applied} to {Speech} enhancement problem}, journal = {RAIRO - Operations Research - Recherche Op\'erationnelle}, pages = {1555--1572}, publisher = {EDP-Sciences}, volume = {54}, number = {6}, year = {2020}, doi = {10.1051/ro/2019106}, mrnumber = {4150245}, language = {en}, url = {http://www.numdam.org/articles/10.1051/ro/2019106/} }
TY - JOUR AU - Ouznadji, Said AU - Chaabane, Djamal AU - Thameri, Messaoud TI - Multiple objective optimization Applied to Speech enhancement problem JO - RAIRO - Operations Research - Recherche Opérationnelle PY - 2020 SP - 1555 EP - 1572 VL - 54 IS - 6 PB - EDP-Sciences UR - http://www.numdam.org/articles/10.1051/ro/2019106/ DO - 10.1051/ro/2019106 LA - en ID - RO_2020__54_6_1555_0 ER -
%0 Journal Article %A Ouznadji, Said %A Chaabane, Djamal %A Thameri, Messaoud %T Multiple objective optimization Applied to Speech enhancement problem %J RAIRO - Operations Research - Recherche Opérationnelle %D 2020 %P 1555-1572 %V 54 %N 6 %I EDP-Sciences %U http://www.numdam.org/articles/10.1051/ro/2019106/ %R 10.1051/ro/2019106 %G en %F RO_2020__54_6_1555_0
Ouznadji, Said; Chaabane, Djamal; Thameri, Messaoud. Multiple objective optimization Applied to Speech enhancement problem. RAIRO - Operations Research - Recherche Opérationnelle, Tome 54 (2020) no. 6, pp. 1555-1572. doi : 10.1051/ro/2019106. http://www.numdam.org/articles/10.1051/ro/2019106/
From maskee to audible noise, in perceptual speech enhancement. Int. J. Signal Process. 5 (2008) 93–96.
, , and ,Improved particle swarm optimization for dual channel speech enhancement. In: International Conference on Signal Acquisition and Processing. IEEE (2010).
and ,Speech enhancement using particle swarm optimization techniques. In: International Conference on Measuring Technology and Mechatronics Automation. IEEE (2010) 441–444. | DOI
and ,Speech Recognition and Synthesis. CRC Press (2001).
and ,Enhancement of speech corrupted by acoustic noise. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-79 (1979) 208–211. | DOI
, , and ,Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27 (1979) 113–120. | DOI
,Contribution à l’Optimisation Multicritère en Variables Discrètes, Ph.D. thesis, UMONS, Polytechnique Faculty of Mons, Belgium (2007).
,Review of speech enhancement techniques using statistical approach. In Vol 5 of International Journal of Electronics Communication and Computer Engineering. Technovision-2014 (2014).
and ,A new optimizer using particles swarm theory. In: Proceedings of the Sixth International Symposium on Micro Machine and Human Science. IEEE Press, Piscataway, NJ, Nagoya, Japan (1995) 39–43. | DOI
and ,Multicriteria Optimization, 2nd ed. Springer, Berlin Heidelberg (2005). | MR | Zbl
,Survey on quality and intelligibility offered by speech enhancement algorithms. In: International Conference on Computing Communication Control and Automation. IEEE (2015).
and ,Proper efficiency and the theory of vector maximization. J. Math. Anal. App. 22 (1968) 618–630. | DOI | MR | Zbl
,Power spectral density error analysis of spectral subtraction type of speech enhancement methods. EURASIP J. Adv. Signal Process. 2007 (2006) 096384. | DOI
,An MMSE estimator for speech enhancement under a combined stochastic-deterministic speech model. IEEE, Trans. Audio Speech Lang. Process. 15 (2007) 406–415. | DOI
, and ,Design and implementation of text to speech conversion for visually impaired people. In: Vol. 7 of International Journal of Applied Information Systems (IJAIS). Foundation of Computer Science FCS, New York, USA (2014).
, and ,Swarm Intelligence. Morgan Kaufmann Publ, San Francisco (2001).
, and ,Psychoacoustic, Speech and Hearing Aids. World Scientific Publishing Co., Pvt. Ltd. (1995).
,Metaheuristic Applications to Speech Enhancement. In: Springer Briefs in Electrical and Computer Engineering, Speech Technology, Amy Neustein, Fort, NJ, USA Lee (2016). | DOI
and ,A new approch to dual channel speech enhanced based on hybrid PSOGSA. Int. J. Speech Technol. 18 (2015) 45–56. | DOI
, , and ,The application of nonlinear spectral subtraction method on millimeter wave conducted speech enhancement. Math. Probl. Eng. 2010 (2010) 371782. | Zbl
, and ,Single Channel Speech Enhancement Using Complex Kalman Filter in Noisy Reverberant Environments. Mobimedia, Qingdao, China (2018).
, and ,Speech Enhancement: Theory and Practice. 2nd ed., CRC Press (2017).
,Multiple objective optimization applied to speech enhancement problem. In: 2017 International Conference on Mathematics and Information Technology (ICMIT) (2017) 24–28. | DOI
, and ,Machine learning applied to audio source separation for audio prosthesis. Master, Université Paris Descartes, École Normale Supérieure, École des Hautes (2017).
,Auditory based spectral amplitude estimators for speech enhancement. In: Vol. 16 of IEEE Transactions on Audio, Speech and Language Processing (2008) 1614–1623. | DOI
and ,Baysien Short-time Spectral Amplitude Estimators for single-Channel Speech Enhancement. Thèse de doctoratUniversité McGill (2009), p. 168.
,A novel approach to speech enhancement using modified spectral subtraction. IJAREEIE 6 (2017) 291–296.
and ,The use of deep learning in speech enhancement. In: Vol. 14 of Proceedings of the First International Conference on Information Technology and Knowledge Management. ACSIS (2018) 107–111. | DOI
and ,Performance analysis of spectral subtraction method for speech enhancement. In: Special Issue from 2nd National Conference on Computing, Electrical, Electronics and Sustainable Energy Systems, Rajahmundry, India (2017).
and ,A hybrid approach for noise reduction using wiener filter and wavelet transform. Int. J. Pure Appl. Math. 119 (2018) 731–743.
and ,Perceptual subspace speech enhancement with variance normalization. Proc. Comput. Sci. 54 (2015) 818–828. | DOI
and ,Advanced Digital Signal Processing and Noise Reduction. 4th ed.. John Wiley & Sons, Ltd. (2008).
,Various methods for speech intelligibility enhancement: a brief survey. IJEEE 8 (2016).
and ,DNN-Based AR-Wiener Filtering for Speech Enhancement, ICASSP. IEEE (2018) 2901–2905.
and ,On Modification and Application of the artificial bee colony algorithm, J. Inf. Process. Syst. 14 (2018) 448–454.
, and ,Cité par Sources :