Harmonizing Identities

My individualized and interdisciplinary PhD research and program proposal explores the intersection of electronic arts, human-centered design, and natural language processing in the pursuit of voice restoration and identity empowerment. It is anchored in the complex dynamics of the human voice and its artificial reconstruction. 
This project seeks to bridge technological innovation with human need, focusing on individuals who have experienced radical voice transformations due to conditions such as total laryngectomy or gender-affirming procedures.
Drawing upon an interdisciplinary methodology, the study emphasizes collaboration with communities and professionals across diverse fields to engage in participatory design. The aim is to develop accessible, tailored speech interfaces that resonate with users' identities and experiences.
Central to this investigation is the development of innovative interfaces for nuanced vocal control; these technologies aim to facilitate speech synthesis while enabling expressive, musical engagement, thereby contributing to a sense of identity restitution and empowerment.
The research is informed by a comprehensive review of artificial speech technologies, visual speech recognition, and silent speech interfaces. It reflects on the historical evolution of these technologies and their current limitations. Additionally, it addresses broader societal and ethical implications, including considerations of accessibility, equity, and the human right to communication. Which means that finding feeds the public policy sphere.
By synthesizing insights from electronic arts, design, computer science, and health sciences, this project contributes to a holistic understanding of voice, identity, and technology as the medium for innovation ecosystems. It underscores the potential of interdisciplinary approaches to create inclusive and empathetic approaches to complex problems disputing definitions and current 
implementations of Human-Centered Design.