A Comprehensive Review of Speech Signal Processing, Voice Activity Detection, and Automatic Speech Recognition: Techniques, Challenges, and Future Directions
International Journal of Communication Systems and Network Technologies · 31.12.2025 · 14 (3) · 193-212
DOI: 10.18486/ijcsnt/14.3.017 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Communication Systems and Network Technologies, online erschienen am 31.12.2025. Verfasst von Sapna Rajput und 2 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Speech signal processing has become one of the most critical enablers of modern human–computer interaction, under-pinning technologies ranging from voice assistants and telephony to clinical diagnostics and security systems. This paper presents a comprehensive and systematic review of the field, spanning three tightly coupled domains: (i) fundamental speech signal analysis and preprocessing, (ii) voice activity detection (VAD), and (iii) automatic speech recognition (ASR). We begin by examining the physical and mathematical foundations of speech production and perception, followed by a detailed treatment of classical and contemporary feature extraction methods, including Mel-Frequency Cepstral Coefficients (MFCC), Linear Predictive Coding (LPC), Perceptual Linear Prediction (PLP), filter-bank features, and learned representations produced by deep neural networks. For VAD, we critically compare energy-based, statisti-cal, model-driven, and end-to-end deep learning approaches with respect to accuracy, latency, and robustness under diverse noise conditions. In the ASR domain, we trace the evolution from hid-den Markov model (HMM) systems through hybrid HMM–deep-neural-network (DNN) architectures to fully neural sequence-to-sequence models, including connectionist temporal classifica-tion (CTC) and attention-based encoder–decoder frameworks. Benchmark performance metrics across standardised datasets (TIMIT, LibriSpeech, CHiME, VoxCeleb) are consolidated and discussed. We further identify persistent open challenges—environmental noise, speaker variability, low-resource languages, and real-time edge deployment—and outline promising research directions, including self-supervised pre-training, multimodal fusion, federated learning, and neuromorphic processing. The survey is intended to serve as a unified reference for researchers and practitioners working at the intersection of signal processing, machine learning, and human–computer interaction.
Zitieren
APA
Rajput, S., Pandey, S., & Mishra, T. (2025). A Comprehensive Review of Speech Signal Processing, Voice Activity Detection, and Automatic Speech Recognition: Techniques, Challenges, and Future Directions. International Journal of Communication Systems and Network Technologies, 14(3), 193-212. https://doi.org/10.18486/ijcsnt/14.3.017
Vancouver
Rajput S, Pandey S, Mishra T. A Comprehensive Review of Speech Signal Processing, Voice Activity Detection, and Automatic Speech Recognition: Techniques, Challenges, and Future Directions. International Journal of Communication Systems and Network Technologies. 2025;14(3):193-212. doi:10.18486/ijcsnt/14.3.017
BibTeX
@article{Rajput2025,
author = {Rajput, Sapna and Pandey, Stuti and Mishra, Tanushka},
title = {A Comprehensive Review of Speech Signal Processing, Voice Activity Detection, and Automatic Speech Recognition: Techniques, Challenges, and Future Directions},
journal = {International Journal of Communication Systems and Network Technologies},
year = {2025},
volume = {14},
number = {3},
pages = {193--212},
doi = {10.18486/ijcsnt/14.3.017}
}
EUVIMED