EUVIMEDEUVIMED entdecken
Crossref

DDSE: Efficient Neural Codec Language Models for speech enhancement with disentangled representations

Qinwen Hu, Xiaobin Rong, Mansur Yesilbursa, Kamil Wojcicki, Tong Lei, Jing Lu

Speech Communication · 2026-07 · 182 · 103428

DOI: 10.1016/j.specom.2026.103428 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Speech Communication, 2026-07. Verfasst von Qinwen Hu und 5 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Hu, Q., Rong, X., Yesilbursa, M., Wojcicki, K., Lei, T., & Lu, J. (2026). DDSE: Efficient Neural Codec Language Models for speech enhancement with disentangled representations. Speech Communication, 182, 103428. https://doi.org/10.1016/j.specom.2026.103428

Vancouver

Hu Q, Rong X, Yesilbursa M, Wojcicki K, Lei T, Lu J. DDSE: Efficient Neural Codec Language Models for speech enhancement with disentangled representations. Speech Communication. 2026;182:103428. doi:10.1016/j.specom.2026.103428

BibTeX
@article{Hu2026,
  author = {Hu, Qinwen and Rong, Xiaobin and Yesilbursa, Mansur and Wojcicki, Kamil and Lei, Tong and Lu, Jing},
  title = {DDSE: Efficient Neural Codec Language Models for speech enhancement with disentangled representations},
  journal = {Speech Communication},
  year = {2026},
  volume = {182},
  pages = {103428},
  doi = {10.1016/j.specom.2026.103428}
}
Kostenlos starten →