İŞİTSEL KORTEKSİN GÜRÜLTÜDEKİ SESLERİ ALGILAMAK İÇİN KONTRASTA UYUM SAĞLAMASI

Fatma Özcan

doi:10.17780/ksujes.1757598

TR EN

İŞİTSEL KORTEKSİN GÜRÜLTÜDEKİ SESLERİ ALGILAMAK İÇİN KONTRASTA UYUM SAĞLAMASI

Öz

Zorlu işitme koşullarında, işlevini yerine getirebilmek için çok çeşitli mekanizmalar geliştiren işitme sistemi, çevresel bilgileri kullanarak kaynakları birbirinden ayırmalıdır. Amacımız, işitsel korteksteki nöronal aktivitenin, çeşitli gürültü seviyelerinde davranışsal performansı öngörüp öngörmediğini doğrulamaktır. Bu çalışmada, derin öğrenme teknikleri kullanılarak, gürültülü bir ortamda, hedef sesin varlığı ve yoğunluğunun işitsel kortekste nasıl kodlandığı incelenmiştir. Nöronal veriler, Skalogram veya Mel-spektrogram görüntülere dönüştürülmüştür. Bu görüntüler seslerle önceden eğitilmiş yapay sinir ağı ile işlenmiştir ve sonuçlar karşılaştırılmıştır. Nöronal kodlama kapsamında, hedef sesin yüksek veya düşük gürültü ortamında mevcut olup olmadığı ve 6 hedef ses seviyesinin ayırt edilip edilemeyeceği analiz edilmiştir. Yüksek veya düşük kontrast içerisinde hedef sesin varlığının ve seviyesinin beyinde kodlanması değerlendirilmiştir. Yüksek kontrastta en zayıf hedef ses, %90,4 AUC değeriyle tespit edilirken, düşük kontrastta en zayıf hedef ses, %100 AUC değeriyle sınıflandırılmıştır. Bu işlemin anlaşılması, duyusal engelli kişilere yardımcı olabilecek yapay sistemlerin geliştirilmesine olanak sağlayacaktır.

Anahtar Kelimeler

THE AUDITORY CORTEX ADAPTS TO CONTRAST IN ORDER TO PERCEIVE SOUNDS IN NOISE

Abstract

In challenging hearing conditions, the auditory system, which has developed a wide variety of mechanisms to perform its function, must distinguish between sources using environmental information. Our aim is to verify whether neuronal activity in the auditory cortex predicts behavioural performance at various noise levels. In this study, deep learning techniques were used to investigate how the presence and intensity of the target sound are encoded in the auditory cortex in a noisy environment. Neuronal data were converted into Scalogram or Mel-spectrogram images. These images were processed using an artificial neural network pre-trained with sounds, and the results were compared. Within the scope of neural coding, it was analysed whether the target sound was present in high or low noise environments and whether 6 target sound levels could be distinguished. The encoding of the target sound's presence and level in the brain within high or low contrast was evaluated. In high contrast, the weakest target sound was detected with an AUC value of 90.4%, while in low contrast, the weakest target sound was classified with an AUC value of 100%. Understanding this process will enable the development of artificial systems that could assist individuals with sensory impairments.

Keywords

References

Abrams, E. B., Marantz, A., Krementsov, I., & Gwilliams, L. (2025). Dynamics of Pitch Perception in the Auditory Cortex. J Neurosci, 45(12). https://doi.org/10.1523/JNEUROSCI.1111-24.2025
Alishbayli, A. (2024). Processing of Statistically Defined Sounds in the Auditory Cortex. https://hdl.handle.net/2066/301602
Angeloni, C. F., Mlynarski, W., Piasini, E., Williams, A. M., Wood, K. C., Garami, L., . . . Geffen, M. N. (2023). Dynamics of cortical contrast adaptation predict perception of signals in noise. Nat Commun, 14(1), 4817. DOI: 10.1038/s41467-023-40477-6
Arandjelovic, R., & Zisserman, A. (2017). Look, Listen and Learn. Paper presented at the 2017 IEEE International Conference on Computer Vision. https://doi.org/10.48550/arXiv.1705.0816
Bisharat, G., Kaganovski, E., Sapir, H., Temnogorod, A., Levy, T., & Resnik, J. (2025). Repeated stress gradually impairs auditory processing and perception. PLoS Biol, 23(2), e3003012. DOI: 10.1371/journal.pbio.3003012
Ceravolo, L., Scariati, J. E., Frühholz, S., Van De Ville, D., & Grandjean, D. (2024). Functional and causal neural mechanisms of human voice perception in noisy situations bioRxiv. doi: https://doi.org/10.1101/2024.10.21.619396
Clayton, K. K., McGill, M., Awwad, B., Stecyk, K. S., Kremer, C., Skerleva, D., . . . Polley, D. B. (2024). Cortical determinants of loudness perception and auditory hypersensitivity. bioRxiv. DOI: 10.1101/2024.05.30.596691
Cramer, J., Wu, H. H., Salamon, J., & Bello, J. P. (2019). Look listen and learn more: design choices for deep audio embeddings. IEEE. DOI: 10.1109/ICASSP.2019.8682475

Kang, H., & Kanold, P. O. (2024). Sparse representation of neurons for encoding complex sounds in the auditory cortex. Prog Neurobiol, 241, 102661. DOI: 10.1016/j.pneurobio.2024.102661
Kell, A. J. E., & McDermott, J. H. (2019). Invariance to background noise as a signature of non-primary auditory cortex. Nat Commun, 10(1), 3958. DOI: 10.1038/s41467-019-11710-y
Lee, T. Y., Weissenberger, Y., King, A. J., & Dahmen, J. C. (2024). Midbrain encodes sound detection behavior without auditory cortex. elife, 12. DOI: 10.7554/eLife.89950
Lilly, J. M., & Olhede, S. C. (2012). Generalized Morse wavelets as a superfamily of analytic wavelets. IEEE Transactions on Signal Processing, 60(11), 6036-6041. DOI: 10.1109/TSP.2012.2210890
Liu, C. (2022). More Performance Evaluation Metrics for Classification Problems You Should Know. https://www.kdnuggets.com/2020/04/performance-evaluation-metrics-classification.html
Mai, A., Hillyard, S. A., & Strauss, D. J. (2025). Linear modeling of brain activity during selective attention to continuous speech: the critical role of the N1 effect in event-related potentials to acoustic edges. Cogn Neurodyn, 19(1), 110. https://doi.org/10.1007/s11571-025-10289-z(0
Marios Akritas, A. G. A., Jules M Lebert, Arne F Meyer, Maneesh Sahani, Jennifer F Linden. (2024). Nonlinear sensitivity to acoustic context is a stable feature of neuronal responses to complex sounds in auditory cortex of awake mice. elife. https://doi.org/10.7554/eLife.98415.1
Mathworks. (2025). Matlab R2025a. https://www.mathworks.com/products/matlab.html
Olhede, S. C., & Walden, A. T. (2002). Generalized morse wavelets. IEEE Transactions on Signal Processing, 50(11), 2661-2670. DOI: 10.1109/TSP.2002.804066
Özcan, F. (2025). Differentiability of voice disorders through explainable AI. Scientific Reports. https://doi.org/10.1038/s41598-025-03444-3
Özcan, F., & Alkan, A. (2021). Frontal Cortex Neuron Type Classification with Deep Learning and Recurrence Plot. Traitement du Signal. DOI: https://doi.org/10.18280/ts.380327
Özcan, F., & Alkan, A. (2023). Neural decoding of inferior colliculus multiunit activity for sound category identification with temporal correlation and transfer learning. Network-Computation in neural Systems. DOI: 10.1080/0954898X.2023.2282576
Pachitariu, M., Steinmetz, N., Kadir, S., Carandini, M., & Harris, K. (2016). Fast and accurate spike sorting of high-channel count probes with KiloSort. Advances in Neural Information Processing Systems, 29. https://dl.acm.org/doi/pdf/10.5555/3157382.3157595
Shehabi, S., Comstock, D. C., Mankel, K., Bormann, B. M., Das, S., Brodie, H., . . . Miller, L. M. (2025). Individual Differences in Cognition and Perception Predict Neural Processing of Speech in Noise for Audiometrically Normal Listeners. eNeuro, 12(4). DOI: 10.1523/ENEURO.0381-24.2025
Treisman, A. M. (1969). Strategies and models of selective attention. Psychol Rev, 76(3), 282-299. https://doi.org/10.1037/h0027242
Tseng, H. C., & Hsieh, I. H. (2024). Effects of absolute pitch on brain activation and functional connectivity during hearing-in-noise perception. Cortex, 174, 1-18. DOI: 10.1016/j.cortex.2024.02.011
Wang, M., Jendrichovsky, P., & Kanold, P. O. (2024). Auditory discrimination learning differentially modulates neural representation in auditory cortex subregions and inter-areal connectivity. Cell Rep, 43(5), 114172. DOI: 10.1016/j.celrep.2024.114172
Yang, L., Wang, S., Chen, Y., Liang, Y., Chen, T., Wang, Y., . . . Wang, S. (2024). Effects of Age on the Auditory Cortex During Speech Perception in Noise: Evidence From Functional Near-Infrared Spectroscopy. Ear Hear, 45(3), 742-752. DOI: 10.1097/AUD.0000000000001460

Details

Primary Language

Turkish

Subjects

Deep Learning , Neural Networks

Journal Section

Research Article

Authors

Fatma Özcan ^*
0000-0001-5112-1046
Türkiye

Publication Date

December 3, 2025

Submission Date

August 3, 2025

Acceptance Date

November 25, 2025

Published in Issue

Year 2025 Volume: 28 Number: 4

DOI

https://doi.org/10.17780/ksujes.1757598

IZ

https://izlik.org/JA73KJ84WS

Cite

RIS / Bibtex

APA

Özcan, F. (2025). İŞİTSEL KORTEKSİN GÜRÜLTÜDEKİ SESLERİ ALGILAMAK İÇİN KONTRASTA UYUM SAĞLAMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(4), 2080-2092. https://doi.org/10.17780/ksujes.1757598