International Symposium on Telecommunication (IST)

Home / 11th International Symposium on Telecommunication (IST'2024)

Attention-Integrated CNN for Precise Sound Source Localization with Microphone Arrays

Authors :

Elham Yazdankhah¹ Salman Karimi²

1- Lorestan University 2- Lorestan University

Keywords :

Convolutional Neural Network،Deep Learning،Microphone Arrays،Feature Extraction،Sound Source Localization

Abstract :

Sound source localization (SSL) in noisy reverberant environments using microphone arrays presents a significant challenge that has garnered considerable research interest. Recent advancements in deep learning have demonstrated improved performance in these classification tasks by rethinking traditional approaches to sound source localization. This paper presents a novel convolutional neural network (CNN) model designed to determine the direction of arrival (DOA) of sound sources in both noisy and reverberant conditions. The model utilizes a combination of time-domain features (root mean square energy) and frequency-domain features (sound intensity, spectral contrast, Mel-frequency cepstral coefficients) extracted from audio signals. To evaluate the model's robustness, three types of experiments were conducted: assessing the impact of additive noise, examining the effects of reverberation time, and analyzing how room conditions influence microphone arrays. The experimental results reveal that the proposed model outperforms existing baseline systems in the literature, achieving the highest accuracy in DOA estimation