Skip to main content
AAO-HNSF 2025 Annual Meeting & OTO EXPO Main banner
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Video

Head and Neck Surgery

(A586) Novel Technologies for Voice Rehabilitation Following Total Laryngectomy: A Review

Monday, October 13, 2025
12:00 PM - 1:00 PM EDT
Location: OTO EXPO, Posters

    Co-Author(s)

  • Zejia Chen, BHSc

    Medical Student
    Faculty of Medicine, Queen’s University, Kingston ON, Canada
    Kingston, Ontario, Canada

    • Presenting Author(s)

  • Noor Al Kaabi, MSc

    Medical Student
    Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada
    Mississauga, Ontario, Canada

    • Co-Author(s)

  • NM

    Nevena Musikic, PhD

    Institute of Biomaterials and Biomedical Engineering University of Toronto, ON, Canada, United States

  • DC

    Douglas B. Chepeha, MD, MPH, FACS, FRCSC

    Adjunct Professor
    Department Otolaryngology Head and Neck Surgery, University of Michigan, Michigan, USA
    Ann Arbor, Michigan, United States

  • JD

    John R. De Almeida, MD, MSc, FRCSC

    Surgeon
    Department of Otolaryngology Head and Neck Surgery, University Health Network, Toronto, Canada
    Toronto, ON, Ontario, United States

  • MP

    Milos R. Popovic, PhD

    Institute of Biomaterials and Biomedical Engineering University of Toronto, ON, Canada, United States

  • ES

    Ervin Sejdic, PhD

    Department of Electrical and Computer Engineering, Faculty of Applied Science and Engineering, University of Toronto, Toronto, ON, Canada, United States

    • Senior Author(s)

  • CY

    Christopher MKL Yao, MD, FRCSC

    Department of Otolaryngology Head and Neck Surgery, University Health Network, Toronto, Canada, United States

Disclosure(s):
Douglas B. Chepeha, MD, MPH, FACS, FRCSC: No relevant relationships to disclose.


Introduction: Loss of voice following a total laryngectomy greatly impacts identity and quality of life, and traditional voice rehabilitation methods are limited in replicating the original voice of the patient. This review describes technological trends in recent voice rehabilitation technology for laryngectomy patients.

Methods: A comprehensive search strategy was developed and a search was conducted in EMBASE, MEDLINE, PubMed, CINAHL, and Web of Science to identify literature studying new speech generation technologies for laryngectomy patients. 633 studies were identified to be screened. Abstract and full-text screening was performed by two study study authors based on inclusion/exclusion criteria, and conflicts were resolved by discussion. 61 studies met inclusion criteria.

Results: Four technological trends were found after review of the literature. One area of research was using using statistical and deep learning models to predict tonality of speech produced by the monotone Electrolarynx. Another area investigated conversion of speech-adjacent signals such as lip movements and articulatory muscle movements to either directly produced speech (articulation-to-speech) or phonemes later converted to speech (silent speech recognition). Another area studied the use of voice banking and text-to-speech systems, which used speech corpora built pre-operatively by patients for personalized speech synthesis post-laryngectomy. Finally, new medical devices implemented existing systems using wearable technology for increased convenience. Many studies outlined improvements in speech naturalness, word recognition, and psychosocial health compared to traditional rehabilitation. However, validation is limited to small cohorts, with better evidence needed to support translation.

Conclusions: This review provides an overview of new technologies for clinical translation and development in voice rehabilitation for laryngectomy patients. While subjective improvements were reported compared to traditional methods, better evidence is still needed to support translation.