Neural network-based modeling for continuous speech recognition in the Uzbek Language

This article presents a description of language models that take into account the unique features of the Uzbek language. Language modeling plays a significant role in improving the accuracy and performance of Automatic Speech Recognition (ASR) systems. Enhancing the conversion of speech to text can be achieved by correctly identifying syntactic and semantic structures in continuous speech. To achieve this goal, statistical and neural network-based language models, including deep learning architectures such as n-grams, Recurrent Neural Networks (RNNs), and transformer models, have been utilized.