Analyzing the recent advancements for Speech Recognition using Machine Learning: A Systematic Literature Analysis

Abstract

Speech Recognition (SR) technology, empowered by Machine Learning (ML) and Deep Learning (DL), has revolutionized human-computer interaction by enabling accurate conversion of spoken language into text or commands. This advancement has found widespread application in consumer electronics, enhancing user engagement through voice commands on devices like smart speakers and smartphones. SR also improves accessibility in sectors such as healthcare and automotive industries, supporting tasks like medical transcription and in-car navigation. This bibliometric study employing the PRISMA model investigates the utilization of Speech Recognition and Machine Learning. Initially, a search yielded 170 results, which were then refined through filters to exclude non-article documents, reducing the collection to 105 articles. Subsequently, inaccessible papers were further removed, resulting in a final list of 35 papers included in the analysis. Ongoing research focuses on enhancing SR's capability to handle diverse accents and languages using advanced deep learning models like RNNs and transformers, aiming to create more intuitive and personalized user experiences through integration with Natural Language Processing (NLP). ML-driven SR continues to drive innovation in AI, promising enhanced efficiency and communication across various domains.