EUVIMEDEUVIMED entdecken
Crossref

Speech Recognition Systems Using Deep Learning Accuracy vs. Efficiency Trade-offs

S.Revathi

Dandao Xuebao/Journal of Ballistics · 29.05.2026 · 38 (2) · 102-112

DOI: 10.52783/dxjb.v38.314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 29.05.2026. Verfasst von S.Revathi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech recognition systems powered by deep learning have transformed human–computer interaction by enabling machines to understand, process, and respond to spoken language with remarkable accuracy. Modern Automatic Speech Recognition (ASR) technologies are widely applied in virtual assistants, healthcare systems, automotive interfaces, smart devices, customer support automation, and real-time translation platforms. Deep learning architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Transformer-based models have significantly improved speech recognition performance by capturing complex temporal and contextual speech patterns. However, increasing recognition accuracy often introduces substantial computational costs, including higher memory consumption, increased latency, energy usage, and processing complexity. This creates a critical trade-off between accuracy and efficiency, particularly in mobile devices, embedded systems, and edge computing environments where computational resources are limited. Recent research focuses on optimizing ASR systems through model compression, quantization, pruning, knowledge distillation, and lightweight neural architectures to achieve real-time performance while maintaining acceptable recognition quality. This paper explores the balance between recognition accuracy and computational efficiency in deep learning–based speech recognition systems, analyzing major architectures, optimization techniques, performance challenges, and emerging approaches for scalable, efficient, and intelligent ASR deployment across modern digital ecosystems.

Zitieren

APA

S.Revathi (2026). Speech Recognition Systems Using Deep Learning Accuracy vs. Efficiency Trade-offs. Dandao Xuebao/Journal of Ballistics, 38(2), 102-112. https://doi.org/10.52783/dxjb.v38.314

Vancouver

S.Revathi. Speech Recognition Systems Using Deep Learning Accuracy vs. Efficiency Trade-offs. Dandao Xuebao/Journal of Ballistics. 2026;38(2):102-112. doi:10.52783/dxjb.v38.314

BibTeX
@article{SRevathi2026,
  author = {S.Revathi},
  title = {Speech Recognition Systems Using Deep Learning Accuracy vs. Efficiency Trade-offs},
  journal = {Dandao Xuebao/Journal of Ballistics},
  year = {2026},
  volume = {38},
  number = {2},
  pages = {102--112},
  doi = {10.52783/dxjb.v38.314}
}
Kostenlos starten →