The Effect of Noise on Speaker Identification and Finding a Noise that Improves Accuracy

DOI: https://doi.org/10.52549/ijeei.v13i3.5867
Published: 30-09-2025 • Issue: Vol. 13 No. 3: September 2025 • Section: Regular paper

Abstract

Conventional Speaker Identification (SID) systems accurately identify speakers if their speech is noiseless. However, their classification accuracies reduce substantially when speech is corrupted by noise. SID systems would be more practical and applicable if they were more noise-robust. We introduce an SID system that can accurately classify speakers, even when their speech is corrupted by various types of noise at different noise levels. We investigate the impact of noisy training data on the performance of an SID system and the noise that may enhance the performance of an SID system. In this paper, we compare two front-end feature extractors: a cochlea model called the Cascade of Asymmetric Resonators with Fast Acting Compression (CAR-FAC) and an FFT-based Gammatone Frequency Cepstral Coefficient (GFCC). We use the Gaussian Mixture Model with the Universal Background Model (GMM-UBM) and a Extreme Learning Machine (ELM) as classifiers to focus on the influence of the front-ends on performance. We train the GMM-UBM and the neural network with noisy data under various conditions to investigate the impact of noise on the classifier. Our results suggest that noisy training data make an SID system noise-robust while the performance under clean conditions remains almost the same. More interestingly, training with speech-shaped noise (cocktail party) enhances SID accuracy more than white noise.

References

B. Saritha, M. A. Laskar, and R. H. Laskar, A Comprehensive Review on Speaker Recognition. Cham: Springer International Publishing, 2023, pp. 3–23. [Online]. Available: https://doi.org/10.1007/ 978-3-031-18444-4 1

N.SaxenaandD.Varshney, “Smarthomesecuritysolutions using facial authentication and speaker recog nition through artificial neural networks,†International Journal of Cognitive Computing in Engineering, vol. 2, pp. 154–164, 2021.

L.Nosrati, A. M. Bidgoli, and H. H. S. Javadi, “Machine learning and metaheuristic algorithms for voice based authentication: A mobile banking case study,†International Journal of Computational Intelligence Systems, vol. 17, no. 1, p. 287, 2024.

Y. Kumar, “A comprehensive analysis of speech recognition systems in healthcare: current research chal lenges and future prospects,†SN Computer Science, vol. 5, no. 1, p. 137, 2024.

J. M. Scanlon, K. D. Kusano, T. Daniel, C. Alderson, A. Ogle, and T. Victor, “Waymo simulated driv ing behavior in reconstructed fatal crashes within an autonomous vehicle operating domain,†Accident Analysis & Prevention, vol. 163, p. 106454, 2021.

C. Badue, R. Guidolini, R. V. Carneiro, P. Azevedo, V. B. Cardoso, A. Forechi, L. Jesus, R. Berriel, T. M. Paixao, F. Mutz et al., “Self-driving cars: A survey,†Expert systems with applications, vol. 165, p. 113816, 2021.

M. Anjum and S. Shahab, “Improving autonomous vehicle controls and quality using natural language processing-based input recognition model,†Sustainability, vol. 15, no. 7, p. 5749, 2023.

F. Thullier, “A practical application of a text-independent speaker authentication system on mobile de vices,†Ph.D. dissertation, Universit´ e du Qu´ ebec ` a Chicoutimi, 2016.

D.P. Ellis, “Plp and rasta and mfcc, and inversion in matlab,†Feb. 2024, http://surl.li/tozjk.

S. Davis and P. Mermelstein, “Comparison of parametric representations for monosyllabic word recogni tion in continuously spoken sentences,†IEEE transactions on acoustics, speech, and signal processing, vol. 28, no. 4, pp. 357–366, 1980.

Y. Shao, S. Srinivasan, and D. Wang, “Incorporating auditory feature uncertainties in robust speaker identification,†in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP’07, vol. 4. IEEE, 2007, pp. IV–277.

Q. Li and Y. Huang, “An auditory-based feature extraction algorithm for robust speaker identification under mismatched conditions,†IEEE transactions on audio, speech, and language processing, vol. 19, no. 6, pp. 1791–1801, 2010.

M. S. Alam and M. S. Zilany, “Speaker identification system under noisy conditions,†in 2019 5th Inter national Conference on Advances in Electrical Engineering (ICAEE). IEEE, 2019, pp. 566–569.

A. Ashar, M. S. Bhatti, and U. Mushtaq, “Speaker identification using a hybrid cnn-mfcc approach,†in 2020 International Conference on Emerging Trends in Smart Technologies (ICETST). IEEE, 2020, pp. 1–4.

M. Tiwari and D. K. Verma, “Enhanced text-independent speaker recognition using mfcc, bi-lstm, and cnn-based noise removal techniques,†International Journal of Speech Technology, vol. 27, no. 4, pp. 1013–1026, 2024.

G. M.Bidelman, F. Bernard, and K. Skubic, “Hearing in categories and speech perception at the “cocktail partyâ€,†PloS one, vol. 20, no. 1, p. e0318600, 2025.

W. Zhang, C. Boeddeker, S. Watanabe, T. Nakatani, M. Delcroix, K. Kinoshita, T. Ochiai, N. Kamo, R. Haeb-Umbach, and Y. Qian, “End-to-end dereverberation, beamforming, and speech recognition with improved numerical stability and advanced frontend,†in ICASSP 2021-2021 IEEE International Confer ence on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021, pp. 6898–6902.

L. Lu, Y. Ding, C. Xue, and L. Li, “Negative emotions in the target speaker’s voice enhance speech recognition under “cocktail-party†environments,†Attention, Perception, & Psychophysics, vol. 83, pp. 247–259, 2021.

Y.-m. Qian, C. Weng, X.-k. Chang, S. Wang, and D. Yu, “Past review, current progress, and challenges ahead on the cocktail party problem,†Frontiers of Information Technology & Electronic Engineering, vol. 19, pp. 40–63, 2018.

R. F. Lyon, Human and machine hearing: extracting meaning from sound. Cambridge University Press, 2017.

M. A. Islam, Y. Xu, T. Monk, S. Afshar, and A. van Schaik, “Noise-robust text-dependent speaker iden tification using cochlear models,†The Journal of the Acoustical Society of America, vol. 151, no. 1, pp. 500–516, 2022.

X. Zhao, Y. Shao, and D. Wang, “Casa-based robust speaker identification,†IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 5, pp. 1608–1616, 2012.

N. Wang, P. Ching, N. Zheng, and T. Lee, “Robust speaker recognition using denoised vocal source and vocal tract features,†IEEE transactions on audio, speech, and language processing, vol. 19, no. 1, pp. 196–205, 2010.

N. Wang, P. C. Ching, N. Zheng, and T. Lee, “Robust speaker recognition using denoised vocal source and vocal tract features,†IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 1, pp. 196–205, 2011.

M. T. Al-Kaltakchi, W. L. Woo, S. S. Dlay, and J. A. Chambers, “Comparison of i-vector and gmm-ubm approaches to speaker identification with timit and nist 2008 databases in challenging environments,†in 2017 25th European Signal Processing Conference (EUSIPCO). IEEE, 2017, pp. 533–537.

R. Jahangir, Y. W. Teh, N. A. Memon, G. Mujtaba, M. Zareei, U. Ishtiaq, M. Z. Akhtar, and I. Ali, “Text independent speaker identification through feature fusion and deep neural network,†IEEE Access, vol. 8, pp. 32187–32202, 2020.

V. Karthikeyan, S. S. Priyadharsini, and K. Balamurugan, “Attention-based multi dimension fused-feature convolutional neural network framework for speaker recognition,†Multimedia Tools and Applications, pp. 1–31, 2025.

Q. Hong, S. Kwong, and H. Wang, “Optimization of gaussian mixture model parameters for speaker identification,†in Genetic and Evolutionary Computation Conference. Springer, 2004, pp. 1310–1311.

D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, and S. Khudanpur, “X-vectors: Robust dnn embed dings for speaker recognition,†in 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 2018, pp. 5329–5333.

D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, “Speaker verification using adapted gaussian mixture models,†Digital signal processing, vol. 10, no. 1-3, pp. 19–41, 2000.

J. H. Hansen and T. Hasan, “Speaker recognition by machines and humans: A tutorial review,†IEEE Signal processing magazine, vol. 32, no. 6, pp. 74–99, 2015.

A. Bakshi and S. K. Kopparapu, “Spoken indian language classification using gmm supervectors and artificial neural networks,†in 2019 IEEE Bombay Section Signature Conference (IBSSC). IEEE, 2019, pp. 1–6. [33] M. Fasounaki, E. B. Y¨ uce, S. ¨ Onc¨ ul, and G. Ë™ Ince, “A comparative assessment of text-independent auto matic speaker identification methods using limited data,†Avrupa Bilim ve Teknoloji Dergisi, no. 26, pp. 217–222, 2021.

G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, “Extreme learning machine: theory and applications,†Neuro computing, vol. 70, no. 1-3, pp. 489–501, 2006.

J. Campbell and A. Higgins, “Yoho speaker verification,†Linguistic Data Consortium, Philadelphia, 1994. [36] R. K. Christensen, H. Lind´ en, M. Nakamura, and T. R. Barkat, “White noise background improves tone discrimination by suppressing cortical tuning curves,†Cell reports, vol. 29, no. 7, pp. 2041–2053, 2019.

D. D. Greenwood, “Critical bandwidth and the frequency coordinates of the basilar membrane,†The Journal of the Acoustical Society of America, vol. 33, no. 10, pp. 1344–1356, 1961.

J. C. Stemple, N. Roy, and B. K. Klaben, Clinical voice pathology: Theory and management. Plural Publishing, 2018.

A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the em algorithm,†Journal of the royal statistical society: series B (methodological), vol. 39, no. 1, pp. 1–22, 1977.

D. A. Reynolds and R. C. Rose, “Robust text-independent speaker identification using gaussian mixture speaker models,†IEEE transactions on speech and audio processing, vol. 3, no. 1, pp. 72–83, 1995.

T. Kinnunen and H. Li, “An overview of text-independent speaker recognition: From features to super vectors,†Speech communication, vol. 52, no. 1, pp. 12–40, 2010.

K.-H. Yuo and H.-C. Wang, “Joint estimation of feature transformation parameters and gaussian mixture model for speaker identification,†Speech Communication, vol. 28, no. 3, pp. 227–241, 1999.

A. Graves and A. Graves, “Long short-term memory,†Supervised sequence labelling with recurrent neu ral networks, pp. 37–45, 2012.

A. Graves, “Long short-term memory,†Supervised sequence labelling with recurrent neural networks, pp. 37–45, 2012.

M. A. Islam, W. A. Jassim, N. S. Cheok, and M. S. A. Zilany, “A robust speaker identification system using the responses from a model of the auditory periphery,†PloS one, vol. 11, no. 7, p. e0158520, 2016.

A. Nagrani, J. S. Chung, and A. Zisserman, “Voxceleb: a large-scale speaker identification dataset,†arXiv preprint arXiv:1706.08612, 2017.

J. H. Rindel, “Restaurant acoustics–verbal communication in eating establishments,†Acoustics in prac tice, vol. 7, no. 1-14, 2019.

M. Islam, M. Zilany, and A. Wissam, “Neural-response-based text-dependent speaker identification un der noisy conditions,†in International Conference for Innovation in Biomedical Engineering and Life Sciences: ICIBEL2015, 6-8 December 2015, Putrajaya, Malaysia 1. Springer, 2016, pp. 11–14.

L. Zhang, F. Schlaghecken, J. Harte, and K. L. Roberts, “The influence of the type of background noise on perceptual learning of speech in noise,†Frontiers in Neuroscience, vol. 15, p. 646137, 2021

Author Biographies

Md Atiqul Islam
International Centre for Neuromorphic Systems, The MARCS Institute for Brain, Behaviour, and Development
Mohammed Abdul Kader
Department of Electrical and Electronic Engineering, Assistant Professor

How to Cite

[1]
M. A. Islam and M. Abdul Kader, “The Effect of Noise on Speaker Identification and Finding a Noise that Improves Accuracy”, IJEEI, vol. 13, no. 3, pp. 814–829, Sep. 2025, doi: 10.52549/ijeei.v13i3.5867.