EUVIMEDEUVIMED entdecken
Crossref

Large Speech Model Enabled Semantic Communication

Yun Tian, Zhijin Qin, Guocheng Lv, Ye Jin, Kaibin Huang, Zhu Han

IEEE Transactions on Mobile Computing · 2026-08 · 25 (8) · 11600-11614

DOI: 10.1109/tmc.2026.3667603 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-08. Verfasst von Yun Tian und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing speech semantic communication systems mainly based on Joint Source-Channel Coding (JSCC) architectures have demonstrated impressive performance, but their effectiveness remains limited by model structures specifically designed for particular tasks and datasets. Recent advances indicate that generative large models pre-trained on massive datasets, can achieve outstanding performance and exhibit exceptional effectiveness across diverse downstream tasks with minimal fine-tuning. To exploit the rich semantic knowledge embedded in large models and enable adaptive transmission over lossy channels, we propose a Large Speech Model enabled Semantic Communication (LargeSC) system. Simultaneously achieving adaptive compression and robust transmission over lossy channels remains challenging, requiring trade-offs among compression efficiency, speech quality, and latency. In this work, we employ the Mimi as a speech codec, converting speech into discrete tokens compatible with existing network architectures. We propose an adaptive controller module that enables adaptive transmission and in-band Unequal Error Protection (UEP), dynamically adjusting to both speech content and packet loss probability under bandwidth constraints. Additionally, we employ Low-Rank Adaptation (LoRA) to fine-tune the Moshi foundation model for generative recovery of lost speech tokens. Simulation results show that the proposed system supports bandwidths ranging from 550 bps to 2.06 kbps, outperforms conventional baselines in speech quality under high packet loss rates and achieves an end-to-end latency of approximately 460 ms, thereby demonstrating its potential for real-time deployment.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Research Grants Council of the Hong Kong Special Administrative Region, China
  • NSFC/RGC CRS
  • Areas of Excellence scheme
  • Collaborative Research Fund
  • Croucher Senior Fellowship, Shenzhen-Hong Kong-Macau Technology Research Programme

Zitieren

APA

Tian, Y., Qin, Z., Lv, G., Jin, Y., Huang, K., & Han, Z. (2026). Large Speech Model Enabled Semantic Communication. IEEE Transactions on Mobile Computing, 25(8), 11600-11614. https://doi.org/10.1109/tmc.2026.3667603

Vancouver

Tian Y, Qin Z, Lv G, Jin Y, Huang K, Han Z. Large Speech Model Enabled Semantic Communication. IEEE Transactions on Mobile Computing. 2026;25(8):11600-11614. doi:10.1109/tmc.2026.3667603

BibTeX
@article{Tian2026,
  author = {Tian, Yun and Qin, Zhijin and Lv, Guocheng and Jin, Ye and Huang, Kaibin and Han, Zhu},
  title = {Large Speech Model Enabled Semantic Communication},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {8},
  pages = {11600--11614},
  doi = {10.1109/tmc.2026.3667603}
}
Kostenlos starten →