EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HASCom: A Heterogeneous Affective-Semantic Communication Framework for Speech Transmission

Zhenjia Yu, Taojie Zhu iD, Md Arman Hossain, Zineb Zbarna, Lei Wang

Sensors · 31.03.2026 · 26 (7) · 2158

DOI: 10.3390/s26072158 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 31.03.2026. Verfasst von Zhenjia Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Portland Institute, Nanjing University of Posts and Telecommunications, Nanjing 220003, China. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This work was supported by the Jiangsu Provincial Key Research and Development 638 Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driven by the development of next-generation wireless networks and the widespread adoption of sensing, communication is shifting from traditional bit-level transmission to intelligent, rich interactions within our digital social system. However, existing speech semantic communication frameworks predominantly focus on textual accuracy, neglecting the critical affective information (e.g., tone and emotion) that is essential for natural human-centric interactions in the real world. To address this limitation, we propose the Heterogeneous Affective Speech Semantic Communication (HASCom) framework, designed for the robust transmission of highly expressive speech over complex wireless channels. Specifically, we design a heterogeneous dual-stream transmission architecture that decouples discrete phoneme-level linguistic content from continuous emotional embeddings. For discrete semantic information, we use reliable digital coding protected by Low-Density Parity-Check (LDPC) to guarantee strict recoverability. Conversely, for emotional features, we employ Deep Joint Source-Channel Coding (JSCC) analog transmission to prevent irreversible quantization errors and the cliff effect. Additionally, we develop a prior-guided diffusion reconstruction module at the receiving end. This module leverages a structural prior network to align the decoded semantics, which then steers the reverse diffusion process conditioned on the recovered affective features. Extensive experiments under both AWGN and Rayleigh fading channels demonstrate that HASCom significantly outperforms state-of-the-art baselines. Specifically, it achieves superior objective semantic similarity and subjective Mean Opinion Score (MOS) at low Signal-to-Noise Ratios (SNRs), while the JSCC transmission modules maintain an ultra-low inference latency of less than 0.1 ms, validating its high efficiency and robustness for practical deployments.

Schlagwörter

Stichwörter der Autor:innen

diffusion modelemotional speechheterogeneous transmissionlowercase communication

Autor:innen und Institutionen

  • Portland Institute, Nanjing University of Posts and Telecommunications, Nanjing 220003, China.
  • School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 220003, China.
  • College of Overseas Education, Nanjing University of Posts and Telecommunications, Nanjing 220003, China.

ORCID-Profile: Taojie Zhu

Förderung

  • This work was supported by the Jiangsu Provincial Key Research and Development 638 Program

Zitieren

APA

Yu, Z., Zhu, T., Hossain, M. A., Zbarna, Z., & Wang, L. (2026). HASCom: A Heterogeneous Affective-Semantic Communication Framework for Speech Transmission. Sensors, 26(7), 2158. https://doi.org/10.3390/s26072158

Vancouver

Yu Z, Zhu T, Hossain MA, Zbarna Z, Wang L. HASCom: A Heterogeneous Affective-Semantic Communication Framework for Speech Transmission. Sensors. 2026;26(7):2158. doi:10.3390/s26072158

BibTeX
@article{Yu2026,
  author = {Yu, Zhenjia and Zhu, Taojie and Hossain, Md Arman and Zbarna, Zineb and Wang, Lei},
  title = {HASCom: A Heterogeneous Affective-Semantic Communication Framework for Speech Transmission},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2158},
  doi = {10.3390/s26072158}
}
Kostenlos starten →