The University of Southampton

Dr Jennifer Williams 

Dr Jennifer Williams is a postdoctoral Research Fellow on the Citizen-Centric AI Systems project. Her current research explores speech/audio solutions to trustworthy and explainable smart energy management. 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 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 (2018), an MS in Computational Linguistics from Georgetown University (2012) and a BA in Applied Linguistics, magna cum laude, from Portland State University (2009).

Research

Research interests

* Smart cities: low-carbon comfort, energy/resource management (rooms/buildings), energy forecasting and summarization

* Audio analysis: room occupancy detection, person activity detection, audio scene understanding, localization

* Privacy: concealing speaker attributes and spoken content

* Ethics: deepfake detection, human/AI perception of deepfakes, attacker signatures, voice ownership

* Speech synthesis: multilingual / code-switched speech, voice conversion, speech disentanglement

* Voice biometrics: speaker verification

* Edge devices: TinyML on ultra-low power devices and chips

Teaching

Speech Signal Processing

Machine Learning  / Deep Learning

Natural Language Processing

Ethics and Controversies in Speech / NLP

Publications

Williams, Jennifer, Comanescu, Ramona, Radu, Oana and Tian, Leimin (2018) DNN Multimodal Fusion Techniques for Predicting Video Sentiment. ACL 2018: 56th Annual Meeting of the Association for Computational Linguistics, Melbourne Convention and Exhibition Centre, Melbourne, Australia. 15 Jul 2018 - 20 Jul 2020 . 64–72 .

Müller, Nicolas M., Dieckmann, Franziska, Czempin, Pavel, Canals, Roman, Böttinger, Konstantin and Williams, Jennifer (2021) Speech is silver, silence is golden: What do ASVspoof-trained models really learn? ASVspoof 2021 Workshop: An official Interspeech 2021 satellite event,, Online. 16 Sep 2021.

Williams, Jennifer (2021) End-to-End Signal Factorization for Speech: Identity, Content, and Style. IJCAI'20 : Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, Yokohama, Yokohama, Japan. 11 - 17 Jul 2020. pp. 5212-5213 .

Gallegos, Pilar Oplustil, Williams, Jennifer, Rownicka, Joanna and King, Simon (2020) An unsupervised method to select a speaker subset from large multi-speaker speech synthesis datasets. Proceedings of the Annual Conference of the International Speech Communication Association: INTERSPEECH 2020, Shanghai, Shanghai, China. 25 Oct 2020 - 29 Oct 2022 . 1758 pp .

Williams, Jennifer, Fong, Jason, Cooper, Erica and Yamagishi, Junichi (2021) Exploring Disentanglement with Multilingual and Monolingual VQ-VAE. 11th ISCA Speech Synthesis Workshop, , Budapest, Hungary. 26 - 28 Aug 2021.

Zhao, Yi, Li, Haoyu, Lai, Cheng-I, Williams, Jennifer, Cooper, Erica and Yamagishi, Junichi (2020) Improved prosody from Learned F0 Codebook representations for VQ-VAE speech waveform reconstruction. Proceedings of the Annual Conference of the International Speech Communication Association: INTERSPEECH 2020, Shanghai, Shanghai, China. 25 Oct 2020 - 29 Oct 2022 . pp. 4417-4421 .

Williams, Jennifer and King, Simon (2019) Disentangling style factors from speaker representations. Interspeech 2019, , Graz, Austria. 15 - 19 Sep 2019. pp. 3945-3949 .

Williams, Jennifer and Rownicka, Joanna (2019) Speech replay detection with x-Vector Attack Embeddings and spectral features. Interspeech 2019, , Graz, Austria. 15 - 19 Sep 2019. pp. 1053-1057 . (doi:10.21437/Interspeech.2019-1760).

[Unknown type: UNSPECIFIED]

Williams, Jennifer, Lellouch, Benjamin, Stein, Sebastian, Vanderwel, Christina and Gauthier, Stephanie (2022) Low-carbon comfort management for smart buildings. IEEE Smart Cities. 26 - 29 Sep 2022.

Share this profile FacebookTwitterWeibo