Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188651,
        author = {SK Sameer and Dr. Surender Kalyan},
        title = {A COMPARATIVE ANALYSIS OF DEEP LEARNING MODELS FOR SPEECH RECOGNITION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {7565-7578},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188651},
        abstract = {Deep learning has changed the game in speech recognition, enhancing the accuracy, robustness and adaptability of speech recognition systems that are utilised in a plethora of areas such as virtual assistants, self-driving vehicles and health. The current paper would offer a comparison of the most imminent deep learning models used in speech recognition, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Deep Neural Networks (DNNs), and the models based on Transformers. Through the critical textual review of performance-based parameters such as Word Error Rate (WER), real-time factor, and model complexity and scalability, this study highlights the strength and weakness of each model and gives us the knowledge of how appropriate they are to various real-life applications. Furthermore, mention the main obstacles of these models, including the data need, generalization, tolerance to noise, computational needs. The comparative study offers an extensive review of the current state of the art in speech recognition nowadays and help researchers and practitioners to select the most appropriate methods of the deep learning to fit the specific application.},
        keywords = {Speech Recognition, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Deep Neural Networks (DNNs), Transformer Models.},
        month = {December},
        }