This project aims to build a multidisciplinary translational team to develop an AI-enabled approach for restoring personalized voice in laryngectomy patients. By integrating clinical expertise and advanced machine learning technologies, the team seeks to create a framework for voice banking and synthesis that preserves patients’ natural vocal identity and improves quality of life.
Specific Aims:
- To engage patients and stakeholders to identify user needs, preferences, and concerns related to voice banking and AI-generated voice technologies.
- To develop a clinical-technical workflow integrating voice/video data capture with AI synthesis tools across pre- and post-operative care.
- To produce planning outputs (protocols, workflows, stakeholder input) to support future pilot funding proposals.
The team combines expertise in head and neck surgery, patient care, engineering, and AI-driven voice synthesis to address a critical unmet need in voice rehabilitation.
Team Building Activities include:
- Stakeholder Workshop: A half-day workshop with patients and caregivers to gather feedback on AI voice features, usability, privacy concerns, and preferences using demonstrations and structured discussions.
- Team Building Coordination: A coordinator supports logistics, meeting organization, and preparation of materials while facilitating collaboration between clinical and technical teams.
- Design & Integration Sessions: A series of collaborative meetings to map workflows, define data integration strategies, and plan deployment of AI voice tools in clinical settings.