Cognitively Inspired Feature Extraction and Speech Recognition for Automated Hearing Loss Testing
Hearing loss, a partial or total inability to hear, is one of the most commonly reported disabilities. A hearing test can be carried out by an audiologist to assess a patient’s auditory system. However, the procedure requires an appointment, which can result in delays and practitioner fees. In addition, there are often challenges associated with the unavailability of equipment and qualified practitioners, particularly in remote areas. This paper presents a novel idea that automatically identifies any hearing impairment based on a cognitively inspired feature extraction and speech recognition approach. The proposed system uses an adaptive filter bank with weighted Mel-frequency cepstral coefficients for feature extraction. The adaptive filter bank implementation is inspired by the principle of spectrum sensing in cognitive radio that is aware of its environment and adapts to statistical variations in the input stimuli by learning from the environment. Comparative performance evaluation demonstrates the potential of our automated hearing test method to achieve comparable results to the clinical ground truth, established by the expert audiologist’s tests. The overall absolute error of the proposed model when compared with the expert audiologist test is less than 4.9 dB and 4.4 dB for the pure tone and speech audiometry tests, respectively. The overall accuracy achieved is 96.67% with a hidden Markov model (HMM). The proposed method potentially offers a second opinion to audiologists, and serves as a cost-effective pre-screening test to predict hearing loss at an early stage. In future work, authors intend to explore the application of advanced deep learning and optimization approaches to further enhance the performance of the automated testing prototype considering imperfect datasets with real-world background noise.
KeywordsHearing loss Speech recognition Machine learning Automation Cognitive radio
The authors would like to acknowledge the support of Prof. Hidayat Ullah from Khyber Teaching Hospital (ENT department) in Pakistan, for his kind support with pure tone and speech audiometry. The authors would like to acknowledge audiologists, Kamran Mulk from Rehman Medical Institute and Muhammad Saeed from Khyber Teaching Hospital for highlighting pure tone and speech audiometry-related issues. The authors would like to acknowledge the support of Dr. Muhammad Arsalan Khan from Khyber Teaching Hospital for inviting participants (patients). Lastly, the authors would like to gratefully acknowledge the support of deepCI and Taibah Valley (Taibah University, Madinah, Saudi Arabia).
This research was supported by deepCI and Taibah Valley (Taibah University, Saudi Arabia).
Compliance with Ethical Standards
This manuscript has not been published in whole or in part elsewhere, which has also not currently being considered for publication in another journal. All authors have been personally and actively involved in substantive work leading to the manuscript, and will hold themselves jointly and individually responsible for its content.
Conflict of interests
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants performed by any of the authors.
- 1.Organization WH, et al. 2013. Millions of People in the World have Hearing Loss that can be Treated or Prevented. Awareness is the Key to Prevention.Google Scholar
- 3.Davis A, Smith P, Ferguson M, Stephens D, Gianopoulos I. Acceptability, benefit and costs of early screening for hearing disability: a study of potential screening tests and models. Health Technology Assessment-Southampton-. 2007;11(42).Google Scholar
- 4.Fagan J. 2014. Open access guide to audiology and hearing aids for otolaryngologists.Google Scholar
- 5.Association ASLH, et al. 2005. Guidelines for manual pure-tone threshold audiometry.Google Scholar
- 10.Martin FN, Clark JG. Introduction to audiology. Boston: Allyn and Bacon; 1997.Google Scholar
- 11.Brandy WT. Speech audiometry. Handb Clin Audiol 2002;5:96–110.Google Scholar
- 12.Franks JR. Hearing measurement. National Institute for Occupational Safety and Health. 2001; p. 183–232.Google Scholar
- 15.Loss CH. 2012. Sensorineural hearing loss. Diseases Ear Nose Throat.Google Scholar
- 16.Pensak ML, Adelman RA. 1993. Conductive hearing loss. Otolaryngology-head and neck surgery St Louis: Mosby Year Book.Google Scholar
- 17.Ramsay HA, Linthicum JF. Mixed hearing loss in otosclerosis: indication for long-term follow-up. Amer J Otol 1994;15(4):536–539.Google Scholar
- 18.Sreedhar J, Venkatesh L, Nagaraja M, Srinivasan P. Development and evaluation of paired words for testing of speech recognition threshold in Telugu A preliminary report. J Indian Speech Lang Hear Assoc 2011;25 (2):128–136.Google Scholar
- 20.Association ASLH, et al. 1988. Determining threshold level for speech.Google Scholar
- 21.Martin FN, Champlin CA, Chambers JA. Seventh survey of audiometric practices in the United States. J-Amer Acad Audiol 1998;9:95–104.Google Scholar
- 22.MD R. 2000. Audiological survey.Google Scholar
- 23.Schoepflin JR. 2015. Back to basics: speech audiometry.Google Scholar
- 26.Szudek J, Ostevik A, Dziegielewski P, Robinson-Anagor J, Gomaa N, Hodgetts B, et al. Can Uhear me now? Validation of an iPod-based hearing loss screening test. Journal of Otolaryngology–Head & Neck Surgery. 2012; p. 41.Google Scholar
- 30.Ananthi S, Dhanalakshmi P. SVM and HMM modeling techniques for speech recognition using LPCC and MFCC features. Proceedings of the 3rd International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2014. Springer; 2015. p. 519–526.Google Scholar
- 31.Chen Ch. Handbook of pattern recognition and computer vision. Singapore: World Scientific; 2015.Google Scholar
- 34.Carhart R, Jerger J. 1959. Preferred method for clinical determination of pure-tone thresholds. Journal of Speech & Hearing Disorders.Google Scholar
- 35.Franks JR. Hearing measurement. National Institute for Occupational Safety and Health. 2001; p. 183–232.Google Scholar
- 39.Nisar S, Khan OU, Tariq M. An efficient adaptive window size selection method for improving spectrogram visualization. Computational intelligence and neuroscience. 2016.Google Scholar
- 40.Dobie RA, Van Hemel S, Council NR, et al. 2004. Basics of Sound, the Ear, and Hearing.Google Scholar
- 41.Schoepflin JR. 2015. Back to Basics: Speech Audiometry.Google Scholar
- 42.Kapul A, Zubova E, Torgaev SN, Drobchik V, Vol. 881. Pure-tone audiometer. In: Journal of Physics: Conference Series. UK: IOP Publishing; 2017, p. 012010.Google Scholar
- 43.Behgam M, Grant SL. Echo cancellation for bone conduction transducers. 2014 48th Asilomar Conference on Signals, Systems and Computers. IEEE; 2014. p. 1629–1632.Google Scholar
- 44.Zhong W, Kong X, You X, Wang B. 2015. Recording Device Identification Based on Cepstral Mixed Features.Google Scholar
- 45.Hsu CW, Chang CC, Lin CJ, et al. 2003. A practical guide to support vector classification.Google Scholar
- 46.Shady Y, Zayed SHH. Speaker independent Arabic speech recognition using support vector machine. Department of Electrical Engineering, Shoubra Faculty of Engineering. Cairo: Benha University; 2009.Google Scholar
- 48.Bhatia N, et al. 2010. Survey of nearest neighbor techniques. arXiv:abs/10070085.
- 49.Breiman L. Bagging predictors. Mach Learn 1996;24(2):123–140.Google Scholar
- 50.Freund Y, Schapire RE. Game theory, on-line prediction and boosting. Proceedings of the ninth annual conference on Computational learning theory. ACM; 1996. p. 325–332.Google Scholar
- 51.Freund Y, Schapire RE, et al. Experiments with a new boosting algorithm. icml; 1996. p. 148–156.Google Scholar
- 53.Dietterich TG. Ensemble methods in machine learning. International workshop on multiple classifier systems. Springer; 2000. p. 1–15.Google Scholar
- 54.Vimala C, Radha V. Isolated speech recognition system for Tamil language using statistical pattern matching and machine learning techniques. J Eng Sci Technol (JESTEC) 2015;10(5):617–632.Google Scholar
- 56.Organization WH, et al. 2014. Deafness and hearing loss. 2015. http://www.who.int/mediacentre/factsheets/fs300/en/ http://www.who.int/mediacentre/factsheets/fs300/en/ (visited on 01/16/ 2016).