Scholar
Colin Lea
Google Scholar ID: TRBVKjIAAAAJ
Apple
Citations & Impact
Citations
4,976
H-index
18
i10-index
20
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published several papers, including:
- - 'Towards AI-driven Sign Language Generation with Non-manual Markers' (CHI 2025, Best Paper Honorable Mention)
- - 'Affect Models Have Weak Generalizability to Atypical Speech' (arXiv 2025)
- - 'Hypernetworks for Personalizing ASR to Atypical Speech' (TACL 2024)
- - 'Community-Supported Shared Infrastructure in Support of Speech Accessibility' (Journal of Speech, Language, and Hearing Research 2024)
- - 'Latent Phrase Matching for Dysarthric Speech' (Interspeech 2023)
- - 'From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition' (CHI 2023)
- - 'Nonverbal Sound Detection for Disordered Speech' (ICASSP 2022)
- - 'Analysis and Tuning of a Voice Assistant System for Dysfluent Speech' (Interspeech 2021)
- - 'SEP-28k: A Dataset for Stuttering Event Detection From Podcasts with People Who Stutter' (ICASSP 2021)
- - 'Audio- and Gaze-driven Facial Animation of Codec Avatars' (Facebook Reality Labs)
Research Experience
- Worked at Facebook Reality Labs from 2017 through 2019 on multimodal avatar animation and multimodal fusion for VR-based telepresence using audio, video, and other sensors as input. During his undergraduate years at the University at Buffalo, he worked on various robotics projects involving unmanned ground vehicles and haptics and led the university's robotics club.
Education
- Defended his PhD in Computer Science at Johns Hopkins University in late 2016, with his primary advisor Greg Hager and co-advisors Rene Vidal and Austin Reiter. His doctoral research focused on developing multimodal models for fine-grained action segmentation.
Background
- A researcher at Apple, focusing on applied machine learning research to improve the accessibility of Apple devices. His primary focus has been on understanding the needs of individuals with speech or motor-speech disabilities and developing new ML systems to enhance their ability to interact with technology. Recently, he led the development of Vocal Shortcuts for iOS18, a personalized speech recognition system designed for people with dysarthria or other speech disabilities. In the past, he led the development of Sound Actions, an iOS15 feature that enables users to interact with an iPhone or iPad using nonverbal sounds like 'pop' or 'click'. Currently, his work involves a mix of time-series ML, data collection/curation, and HCI.
Co-authors