Projects

Working title · Research in progress: Agentic Low-Resource Adaptation and Optimization of On-Device Automatic Speech Recognition for Older Adults’ Clinical Consultations.

My doctoral research investigates how automatic speech recognition systems might be adapted to clinical consultations involving older adults when relevant speech data and computing resources are limited. The proposed research brings together low-resource adaptation, on-device evaluation, and agent-guided experimentation.

The programme aims to examine recognition quality alongside practical deployment requirements, including latency and memory use on actual devices. A further research direction considers whether AI agents can support the selection and execution of adaptation experiments within defined data and computational budgets.

The current phase focuses on critically reviewing the literature, assessing the relevance of existing evidence, and refining research questions and evaluation protocols.

Product context: Jinshou Merchant is a mobile POS and store-management system designed for visually impaired massage clinic owners and entrepreneurs in China. Its goal was to make everyday business workflows more accessible and support independent digital business management.

User research & accessibility: Investigated the needs of users with low vision and users who are blind through regular communication. Explored screen-reader adaptation and non-visual interaction to identify practical barriers and inform requirements, usability decisions, and accessible product design.

Multi-role product planning & design: Led requirements research, functional design, and prototyping across merchant administration, platform administration, customer-facing services, and practitioner and technician interfaces. The merchant experience centered on a mobile app, with the wider system connecting the roles involved in running a clinic.

Core business workflows: Planned store operations, coupon distribution, membership management, order management, online consultation, employment and training enquiries, and technician scheduling. The system connected customer ordering, technician order acceptance, and scheduling through online workflows.

Feedback-driven iteration: Led multiple release iterations and used user feedback to refine features and interactions. The design aimed to help visually impaired merchants manage their stores more independently, reduce administrative and operating burdens, and improve day-to-day efficiency; no quantified cost or efficiency improvement is reported.

Project management & delivery: Created project plans, coordinated tasks across development phases, tracked schedules and quality, and managed development risks through to product delivery.

Recognition: Bronze Award, 6th China International “Internet+” College Students’ Innovation & Entrepreneurship Competition — Guangdong Provincial Competition, Youth Red Dream Journey Track (2020).

Led product design and planning for an AI-powered meeting assistant, with a focus on team collaboration workflows.

The product experience covered speech transcription, summarization, and knowledge organization. Responsibilities included product design, feature planning, and cross-functional delivery.

Shipped core features and supported real-world use in enterprise scenarios.