Speech Recognition Technologies: Design, Challenges, and Real-World Applications

Maruti Maurya; Mohd Zaheer; Nawab Mohammad; Sadaf siddiqui; Mohd Zeeshan Khan; Mohd Ayan Akram

doi:10.55524/ijircst.2025.13.3.9

Abstract

This paper presents an automated speech recognition (ASR) system that transcribes audio from YouTube videos into accurate text using OpenAI's Whisper model. Leveraging tools such as yt_dlp, FFmpeg, and PyTorch, the system creates a robust speech-to-text pipeline. On receiving a video URL, the system extracts and preprocesses audio, transcribes it using Whisper, and evaluates transcription quality through metrics like Word Error Rate (WER), Character Error Rate (CER), and Match Error Rate (MER). The pipeline supports offline use, making it suitable for accessible, cost-effective deployment in educational, research, and assistive applications.

Keywords

OpenAI Whisper Model, YouTube Audio Transcription, Word Error Rate (WER), Character Error Rate (CER), Multilingual Speech Recognition, Audio Preprocessing

References

Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever., "Robust speech recognition via large-scale weak supervision," arXiv preprint arXiv:2212.04356, 2022. Available from: https://arxiv.org/abs/2212.04356
D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. draft, 2023. Available from: https://web.stanford.edu/~jurafsky/slp3/
A. Ali and S. Renals, "Word error rate estimation for speech recognition: e-WER," Proc. 55th ACL Vol. 2, 2017. Available from: https://tinyurl.com/7pk2cf3x
OpenAI, "Whisper: Automatic speech recognition system," 2022. Available from: https://github.com/openai/whisper
yt-dlp, "A youtube-dl fork with additional features and fixes," 2023. Available from: https://github.com/yt-dlp/yt-dlp
FFmpeg, "Record, convert and stream audio and video," 2023. Available from: https://ffmpeg.org/
A. Paszke et al., "PyTorch: An imperative style, high-performance deep learning library," NeurIPS, vol. 32, pp. 8024–8035, 2019. Available from: https://tinyurl.com/mssnt5pz
J. Morris, "jiwer: Compute word error rate and other ASR metrics," 2023. Available from: https://github.com/jitsi/jiwer
V. I. Levenshtein, "Binary codes capable of correcting deletions, insertions, and reversals," Soviet Physics Doklady, vol. 10, no. 8, pp. 707–710, 1966. Available from: https://tinyurl.com/4t4cs82w
"Speech and Language Processing" by Daniel Jurafsky & James H. Martin. Available from: https://tinyurl.com/3ywsje7h
"Fundamentals of Speech Recognition" by Lawrence Rabiner & Biing-Hwang Juang. Available from: https://tinyurl.com/54jb62ue
"Automatic Speech Recognition: A Deep Learning Approach" by Dong Yu & Li Deng. Available from: https://tinyurl.com/5b4wu5sm
IEEE Transactions on Audio, Speech, and Language Processing – Scholarly articles. Available from: https://tinyurl.com/2ccfptn2
"Pattern Recognition and Machine Learning" by Christopher M. Bishop. Available from: https://tinyurl.com/5c3axn78

Cites this article as

M. Maurya, M. Zaheer, N. Mohammad, S. siddiqui, M. Z. Khan, M. A. Akram, "Speech Recognition Technologies: Design, Challenges, and Real-World Applications", International Journal of Innovative Research in Engineering & Management (ijircst), Vol-13, Issue-3, Page No-55-61, 2025. Available from: https://doi.org/10.55524/ijircst.2025.13.3.9

Corresponding Author

Maruti Maurya

Assistant Professor, Department of Computer Science and Engineering, Integral University, Lucknow, India

Download Full Paper

Download PDF

No. of Downloads: 14 | No. of Views: 530

Advancing Education through VR: The Emerging Scope of Virtual Classrooms

Mohd Tanveer, Mohd Azat, Inayat Husain, Sakil Ahmad, Mohammad Aalam Khan.

May 2025 - Vol 13, Issue 3
Deep Learning-based Sentiment Analysis of Text using Long Short-Term Memory Networks

MD Shahid Ali, Saif Ali , Abdullah Parwez, Abu Sufiyan, Mohd Haroon.

May 2025 - Vol 13, Issue 3
Object Detection and Deep Learning

Shra Fatima, Maliha Fatima, Wafa Zaidi.

May 2025 - Vol 13, Issue 3

Speech Recognition Technologies: Design, Challenges, and Real-World Applications

Citations

Download Full Paper PDF

Total View 530

Total Download 14