Rchr
J-GLOBAL ID:201901012372603805
Update date: Apr. 04, 2024
Cooper Erica
Cooper Erica
Affiliation and department:
Job title:
Senior Researcher
Homepage URL (1):
https://ecooper7.github.io/
Research field (1):
Perceptual information processing
Research keywords (2):
Speech processing
, Speech Synthesis
Research theme for competitive and other funds (13):
- 2022 - 2024 Linking Neural Speaker Embeddings with Text
- 2021 - 2024 Language-independent, multi-modal, and data-efficient approaches for speech synthesis and translation
- 2021 - 2023 Can AI storytellers entertain people? - Improving the expressive power of rakugo text-to-speech and automatically generating rakugo stories
- 2022 - 2023 The VoiceMOS Challenge: MOS prediction for synthetic speech
- 2021 - 2022 Optimizing a Speech Anti-spoofing Database
- 2021 - 2022 Enhanced End-to-End Multi-Instrument MIDI/sheet-to-Music Synthesis with Timbre and Style Transfer
- 2021 - 2022 Expressive End-to-End MIDI-to-Performance Music Synthesis
- 2021 - 2022 Improved speech quality assessment models with a large-scale listening test dataset and the application to voice conversion
- 2020 - 2021 Deep Generative Approach to Anti-spoofing Problems
- 2020 - 2021 Transfer Learning for End-to-End Multi-Instrument MIDI-to-Music Synthesis
- 2020 - 2021 Transfer Learning for End-to-End Multi-Instrument MIDI-to-Music Synthesis
- 2019 - 2021 Encoder Factorization for Capturing Dialect and Articulation Level in End-to -End Speech Synthesis
- 2019 - 2020 Robust and all-purpose neural source-filter models
Show all
Papers (50):
-
Chang Zeng, Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi. Joint speaker encoder and neural back-end model for fully end-to-end automatic speaker verification with multiple enrollment utterances. Computer Speech & Language. 2024. 86. 101619-101619
-
Xiaoxiao Miao, Xin Wang, Erica Cooper, Junichi Yamagishi, Nicholas Evans, Massimiliano Todisco, Jean-François Bonastre, Mickael Rouvier. Synvox2: Towards A Privacy-Friendly Voxceleb2 Dataset. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2024
-
Aditya Ravuri, Erica Cooper, Junichi Yamagishi. Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction. IEEE ICASSP 2024 workshop on Self-supervision in Audio, Speech and Beyond. 2024
-
Erica Cooper, Wen-Chin Huang, Yu Tsao, Hsin-Min Wang, Tomoki Toda, Junichi Yamagishi. The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domains. ASRU 2023. 2023
-
Hemant Yadav, Erica Cooper, Junichi Yamagishi, Sunayana Sitaram, Rajiv Ratn Shah. Partial Rank Similarity Minimization Method for Quality MOS Prediction of Unseen Speech Synthesis Systems in Zero-Shot and Semi-supervised setting. ASRU 2023. 2023
more...
MISC (1):
-
Erica Cooper, Xin Wang. Deepfakes: Synthetic media in the age of deep learning. nextrends Asia. 2021
Lectures and oral presentations (9):
-
The VoiceMOS Challenge: Data-Driven Mean Opinion Score Prediction for Synthesized Speech
(2022 Autumn meeting of the Acoustical Society of Japan 2022)
-
How do Machines Speak? Progress and Challenges of Speech Synthesis
(NII Shimin Koza 2022)
-
Objective Evaluation in TTS
(KTH Seminar on Speech Synthesis Evaluation 2022)
-
The VoiceMOS Challenge 2022
(2022)
-
Text-to-Speech Synthesis Techniques for MIDI-to-Audio Synthesis
(2021)
more...
Education (3):
- 2010 - 2019 Columbia University Computer Science Ph.D.
- 2009 - 2010 Massachusetts Institute of Technology Electrical Engineering and Computer Science Master of Engineering
- 2005 - 2009 Massachusetts Institute of Technology Electrical Engineering and Computer Science Bachelor of Science
Committee career (4):
- 2020/12 - 現在 Institute of Electrical and Electronics Engineers Speech and Language Technical Committee (Associate Member)
- 2023/01 - 2023/06 VoiceMOS Challenge 2023 Organizing Committee
- 2021/12 - 2022/03 VoiceMOS Challenge 2022 Organizing Committee
- 2021/08 - 2021/08 Workshop for Young Female Researchers in Speech Science & Technology (YFRSW) Organizing Committee
Awards (1):
- 2023/03 - CREST 11th CREST Research Area Meeting Best Colab Award The VoiceMOS Challenge: MOS prediction of synthetic speech
Return to Previous Page