• Shayan Parwaiz
• Ashirbad Jena
• Anshul Singh

Due to its many uses in speech recognition, music genre categorization, ambient sound monitoring, and other areas, audio classification has attracted a lot of attention in recent years. Comparing deep learning techniques to classic machine learning algorithms, they perform better, making them formidable instruments for audio categorization problems. In this study, we compare the performance of two deep learning architectures for audio categorization tasks: convolutional neural networks (CNNs) and recurrent neural networks (RNNs). For each method, we test two distinct topologies and compare the results using the UrbanSound8K dataset. Our findings shed light on how well RNNs and CNNs perform in audio classification tasks and provide recommendations for selecting appropriate models in accordance with particular needs.

Audio classification, Deep learning, Recurrent neural networks, Convolutional neural networks, UrbanSound8K dataset.

"Deep Learning Architectures for Audio Classification: A Comparative Study of RNNs and CNNs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.j175-j178, April-2024, Available :http://www.jetir.org/papers/JETIR2404921.pdf

"Deep Learning Architectures for Audio Classification: A Comparative Study of RNNs and CNNs", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppj175-j178, April-2024, Available at : http://www.jetir.org/papers/JETIR2404921.pdf