DBN-FTLSTM: An Optimized Deep Learning Framework for Speech and Image Recognition

Abstract

Artificial Intelligence's (AI) quick development has brought about a new era of technical innovation with significant ramifications for many different fields. This study explores the development of artificial intelligence (AI) for image and speech recognition, a job in natural language processing that entails the real-time computer transcription of spoken words. The use of deep learning (DL) models for voice recognition has been the subject of several research. But this field is developing quickly. This systematic review offers a thorough and in-depth analysis of research on voice recognition using DL approaches that was published between 2020 and 2024. In order to improve clarity, this study clearly outlines the methodology, including the dataset size, preprocessing methods (MFCC extraction, normalisation, and augmentation), and benchmarking criteria. To provide openness and repeatability, the datasets used for assessment must be specified in reported performance measures (accuracy, RMSE, MAE, and R²). The dataset, experimental setup, and baseline comparisons should all be explicitly stated in order to contextualise the 99.3% accuracy claim. With an overall performance accuracy rate of 97.90%, a root means square error (RMSE) of 0.017, a mean absolute error (MAE) of 0.01, and an R² value of 98.7%, the DBN-FTLSTM model performs better than existing techniques. When compared to other current approaches, the recommended method's error metrics accuracy of 99.3% is the greatest. Mel-frequency cepstral coefficients were the most often used feature extraction approach, while the word error rate was the most commonly used assessment method. Another finding was the dearth of research using transformers, which have been shown to be effective models that can enable parallelization, speed up learning, and enhance the performance of low-resource languages. The findings also identified intriguing and promising areas for further study that had not gotten much attention in previous investigations