• Ayush Bhardwaj
• Gurvinder Singh
• Bhupen Garg
• Nivedita Vats
• Manish Kumar Singh

Speech-to-text conversion, also known as automatic speech recognition (ASR), has become increasingly important in many applications, including virtual assistants, captioning, and transcription. However, building accurate and robust ASR systems is challenging due to the variability of speech signals, including background noise, speaker accents, and speech styles. In recent years, transfer learning has emerged as a promising technique for improving the performance of deep learning models in various tasks, including natural language processing. In this paper, we investigate the effectiveness of transfer learning in the context of speech-to-text systems. the potential of transfer learning in improving the accuracy and robustness of speech-to-text systems. This approach has practical implications for building ASR systems in various domains and scenarios.

Speech-to-text, automatic speech recognition, transfer learning, fine-tuning, feature extraction, deep learning.

"A Comparative Study of AI Techniques for Speech-to-Text Conversion", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 11, page no.e44-e48, November-2023, Available :http://www.jetir.org/papers/JETIR2311407.pdf

"A Comparative Study of AI Techniques for Speech-to-Text Conversion", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 11, page no. ppe44-e48, November-2023, Available at : http://www.jetir.org/papers/JETIR2311407.pdf