Jennifer Williams
Jennifer Williams
Assistant Professor at University of Southampton (UK)
Verified email at - Homepage
Cited by
Cited by
Recognizing Emotions in Video Using Multimodal DNN Feature Fusion
J Williams, S Kleinegesse, R Comanescu, O Radu
ACL 2018 Grand Challenge and Workshop on Human Multimodal Language …, 2018
Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?
NM Müller, F Dieckmann, P Czempin, R Canals, K Böttinger, J Williams
2021 Edition of the Automatic Speaker Verification and Spoofing …, 2021
Human Perception of Audio Deepfakes
NM Müller, K Markert, J Williams
First International Workshop on Deepfake Detection for Audio Multimedia at …, 2021
Disentangling Style Factors from Speaker Representations
J Williams, S King
Proc. Interspeech 2019, 3945-3949, 2019
DNN Multimodal Fusion Techniques for Predicting Video Sentiment
J Williams, R Comanescu, O Radu, L Tian
ACL 2018, 64, 2018
Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth
J Williams, CK Dagli
EACL 2017 VarDial Workshop, 73–83, 2017
Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis
J Williams, J Rownicka, P Oplustil, S King
Speaker Odyssey Workshop, 2020, 2020
A Language-Independent Approach to Automatic Text Difficulty Assessment for Second-Language Learners
W Shen, J Williams, T Marius, S E
ACL 2013 PITR Workshop, 30, 2013
Speech Replay Detection with x-Vector Attack Embeddings and Spectral Features
J Williams, J Rownicka
Proc. Interspeech 2019, 1053-1057, 2019
Extracting and Modeling Durations for Habits and Events from Twitter
J Williams, G Katz
ACL 2012, 223-227, 2012
Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm
J Williams, Y Zhao, E Cooper, J Yamagishi
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction
Y Zhao, H Li, CI Lai, J Williams, E Cooper, J Yamagishi
Proc. Interspeech 2020, 2020
An Unsupervised Method to Select a Speaker Subset from Large Multi-Speaker Speech Synthesis Datasets
PO Gallegos, J Williams, J Rownicka, S King
Proc. Interspeech 2020, 1758--1762, 2020
Attacker Attribution of Audio Deepfakes
NM Müller, F Dieckmann, J Williams
Proc. Interspeech 2022, 2788--2792, 2022
Extracting Fine-Grained Durations for Verbs from Twitter
J Williams
ACL 2012 (SRW), 49-54, 2012
New challenges for content privacy in speech and audio
J Williams, K Pizzi, S Das, PG Noé
Proc. 2nd Symposium on Security and Privacy in Speech Communication, 1-6, 2022
Revisiting Speech Content Privacy
J Williams, J Yamagishi, PG Noé, C Valentini-Botinhao, JF Bonastre
1st ISCA Symposium of the Security & Privacy in Speech Communication, 2021
Exploring Disentanglement with Multilingual and Monolingual VQ-VAE
J Williams, J Fong, E Cooper, J Yamagishi
Proc. 11th ISCA Speech Synthesis Workshop (SSW 11), 124--129, 2021
Safe Audio AI Services in Smart Buildings
J Williams, V Yazdanpanah, S Stein
ACM BuildSys 2022, 2022
Finding Good Enough: A Task-Based Evaluation of Query Biased Summarization for Cross-Language Information Retrieval
J Williams, S Tam, W Shen
Empirical Methods in Natural Language Processing (EMNLP), 2014
The system can't perform the operation now. Try again later.
Articles 1–20