Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulation
To the best of our knowledge, no prior work has explored the application of AVSE to CI simulations. This study provides the first evidence that incorporating visual information can significantly improve the intelligibility of vocoded speech in CI scenarios.
Authors
- Tughrul Arslan (ORCID: https://orcid.org/0000-0001-8176-5803)
- Yu Tsao (ORCID: https://orcid.org/0000-0001-6956-0418)
- Richard Lee Lai
- Jen-Cheng Hou (ORCID: https://orcid.org/0000-0002-4010-0220)
- Amir Hussain (ORCID: https://orcid.org/0000-0002-8080-082X)
- Chii‐Wann Lin (ORCID: https://orcid.org/0000-0002-8721-3441)
- Mandar Gogate (ORCID: https://orcid.org/0000-0003-1712-9014)
- Kuo-Hsuan Hung (ORCID: https://orcid.org/0009-0007-0974-4873)
- I-Chun Chern
- Yi‐Ting Chen
Institutions
- National Taiwan University (TW)
- Edinburgh Napier University (GB)
- Research Center for Information Technology Innovation, Academia Sinica (TW)
- University of Edinburgh (GB)
Publication Details
- Journal
- IEEE Transactions on Biomedical Engineering
- Published
- 2025-10-02
- DOI
- https://doi.org/10.1109/tbme.2025.3610284
- Citations
- 3
- Primary Topic
- Hearing Loss and Rehabilitation
- Type
- article
- Field-Weighted Citation Impact
- 4.29