Overview*
The candidate will support innovation and technology projects under ARCHIVE and Healthcare Redesign. He/She will be working on projects applying Artificial Intelligence and Machine Learning (AI/ML) to develop advanced tools for speech therapy. This role involves collaboration with a dynamic team of researchers from NUS School of Computing and clinical experts to design, develop, and evaluate AI-driven models and applications aimed at enhancing speech therapy delivery process.
Job Responsibilities*
You will be responsible for the following:
1. Organize existing relevant speech datasets as well as newly collected speech datasets
2. Write python scripts for data loading, training speech recognition models and inference
3. Develop a web interface for real-time access of the trained model
4. Participate in testing and validation of developed technologies in clinical settings to ensure efficacy and safety
5. Contribute to writing scientific papers, report and grant proposals.
6. Support project team in daily administrative tasks and project management and project management activities.
Requirements*
- Bachelor or Master’s degree in Computer Science or related field
- Proficient in neural networks frameworks such as pytorch
- Preferably experienced in automatic speech recognition topics
- Speech or Audio research experience, with publication submissions for relevant conferences such as ICASSP or Interspeech.
- Good verbal and written communication skills
- Ability to work collaboratively in a multidisciplinary team environment
- Prior exposure to or interest in healthcare and clinical applications is highly desirable
