Talk · IEEE International Conference on Smart Information Systems and Technologies · May 15, 2024

Research and development of an information system for speech recognition based on neural network algorithms metrics

Мақсат Қанашев, Assel Mukasheva, Didar Yedilkhan, Sabina Rakhmetulayeva, Sergiy O. Gnatyuk, Nazym Mirambayeva

Read on dx.doi.orgDOI 10.1109/sist61555.2024.10629440

Abstract

This article examines the parameters of speech recognition in audio recordings containing a variety of phrases uttered by different people with different accents and intonations. The aim of the study is to evaluate the recognition speed, the accuracy of audio-to-text conversion and resource consumption when using SpeechRecognition and Levenshtein libraries. During the analysis, the above libraries were used to record and recognize audio files, as well as to calculate the distance between two lines and determine the recognition accuracy. The findings of this study can be useful for improving speech recognition systems and creating more adaptive and efficient solutions for audio data processing. The results of comparing the accuracy of speech recognition models are recorded in JSON format, after which, using the matplotlib library, they are visualized as graphs, comparing the speed and accuracy of recognition. Visualization of data in this way contributes to their improvement and more effective integration into educational systems. In conclusion, the authors emphasize the prospects for further development of speech recognition technologies in different fields.

Speech Recognition and SynthesisSpeech and Audio ProcessingSpeech and dialogue systemsspeech recognitionaudio-to-text conversionLevenshtein distance

Research and development of an information system for speech recognition based on neural network algorithms metrics

Abstract

More by Assel Mukasheva