About
Dr Jennifer Williams is a postdoctoral Research Fellow on the Citizen-Centric AI Systems project and she is PI of a UKRI TAS Agile project on trustworthy audio. Her current research explores speech/audio solutions to trustworthy and explainable smart energy management. She completed her PhD at University of Edinburgh in the area of representation learning and speech signal disentanglement applied to a variety of speech technology applications (voice conversion, speech synthesis, anti-spoofing, naturalness assessment, and privacy). Before her doctoral work, she was a staff member at MIT Lincoln Laboratory for five years where she developed rapid prototyping solutions for text and speech technology. She is a member of IEEE and ISCA, serves as a committee member of the ISCA-PECRAC group, and co-organizes ISCA SPSC-SIG events. She is a reviewer for multiple conferences involving AI, text, speech, and multimedia. She holds an MScR in Data Science from University of Edinburgh, an MS in Computational Linguistics from Georgetown University (USA), and a BA in Applied Linguistics, magna cum laude, from Portland State University (USA).
Research
Research groups
Research interests
- Dr Williams conducts research in responsible and trustworthy audio processing applied to a variety of domains and use-cases. Along these lines, her research also addresses issues of audio AI safety in terms of usability, privacy, and security. These issues overlap with procesing in edge devices (e.g., ultra low-power devices). Her work addresses ethical issues of trust for audio AI, spanning a breadth of topics such as: deepfake detection, voice-related rights, and speaker and content privacy.
Current research
Dr Williams conduct research in audio processing as it is applied to smart cities and smart buildings. She investigates connections between audio AI services in smart buildings that can detect and analyse occupant presence, movement, and activity levels and incorporating this information into reinforcement learning algorithms to simultaneously optimise resource consumption (energy, ventilation, cost, etc) with occupant preferences and comforts.
Along these lines, her research also addresses issues of audio AI safety in terms of usability, privacy, and security. These issues overlap with procesing in edge devices (e.g., ultra low-power devices and chips via TinyML). Her work addresses ethical issues of trust for audio AI, spanning a breadth of topics such as: deepfake detection, voice as a form of property, and speaker and content privacy.
Publications
Supervision
Current PhD Students
Teaching
Speech Signal Processing
Machine Learning / Deep Learning
Natural Language Processing
Ethics and Controversies in Speech / NLP
External roles and responsibilities
Biography
Dr Jennifer Williams is an assistant professor in Electronics and Computer Science. Her current research explores creation of trustworthy, private, and secure speech/audio solutions and explainable smart building services such as occupancy-based smart energy management. Dr. Williams is the PI of a large interdisciplinary project from the UKRI Trustworthy Autonomous Systems Hub (TAS Hub) on trustworthy audio. She completed her PhD at University of Edinburgh (2021) in the area of representation learning and speech signal disentanglement for a variety of speech technology applications (voice conversion, speech synthesis, anti-spoofing, naturalness assessment, and privacy). Before her doctoral work, she was a staff member at MIT Lincoln Laboratory for five years where she developed rapid prototyping solutions for text and speech technology. She has conducted research in Tokyo, Japan as well as Singapore. She is a member of IEEE and ISCA (International Speech Communication Association), serves as a committee member of the ISCA-PECRAC group (Postdoctoral and Early Career Research Advisory Committee), and is a reviewer for multiple conferences involving AI, text, speech, and multimedia. Dr. Williams is also the Chair of the ISCA special interest group on Security and Privacy in Speech Communication (SPSC-SIG). She is also Co-Chair for the Interspeech 2023 Special Sessions. She holds an MScR in Data Science from University of Edinburgh (2018), an MS in Computational Linguistics from Georgetown University (2012) and a BA in Applied Linguistics, magna cum laude, from Portland State University (2009).