In recent years, significant advancements have been made in deep learning technology within the field of speech applications, which has resulted in an increased interest in accent classification. The growing need for accurate speech recognition technology requires enhancing the ability of machines to identify accents, which results in giving a critical challenge in speech processing. The variety of English accents poses significant difficulties for automated speech recognition (ASR) systems, adversely impacting transcription accuracy and speaker intelligibility. This study aims to address this challenge by developing a deep learning model efficient in accurately classifying regional English dialects throughout the United Kingdom and Ireland. The proposed system combines a one-dimensional Convolutional Neural Network with a Gated Recurrent Unit (1D-CNN-GRU) architecture and utilizes Mel-Frequency Cepstral Coefficients (MFCCs) as acoustic features. The UK and Ireland English Dialect (UIED) dataset, consisting of 17,877 recordings across six accent categories (Welsh, Northern, Southern, Scottish, Irish, and Midlands English), was utilized for assessment. Experimental results indicate that the proposed model surpasses previous techniques, with an accuracy of 98.71%, hence underscoring its efficacy in capturing accent-specific temporal and spectral patterns. The findings improve the development of accent-resistant ASR systems and establish a basis for future research using transformer-based embedding and prosodic characteristics.