TY - GEN
T1 - Generative Data Augmentation Challenge
T2 - 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2025
AU - Bae, Jae Sung
AU - Kuznetsova, Anastasia
AU - Manocha, Dinesh
AU - Hershey, John
AU - Kristjansson, Trausti
AU - Kim, Minje
N1 - This material is in part based on work supported by the National Science Foundation under grant numbers, 2512987 and 1910940.
PY - 2025
Y1 - 2025
N2 - This paper presents a new challenge that calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as part of the Generative Data Augmentation workshop at ICASSP 2025. Collecting high-quality personalized data is challenging due to privacy concerns and technical difficulties in recording audio from the test scene. To address these issues, synthetic data generation using generative models has gained significant attention. In this challenge, participants are tasked first with building zero-shot TTS systems to augment personalized data. Subsequently, PSE systems are asked to be trained with this augmented personalized dataset. Through this challenge, we aim to investigate how the quality of augmented data generated by zero-shot TTS models affects PSE model performance. We also provide baseline experiments using open-source zero-shot TTS models to encourage participation and benchmark advancements. Our baseline code implementation and checkpoints are available online.
AB - This paper presents a new challenge that calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as part of the Generative Data Augmentation workshop at ICASSP 2025. Collecting high-quality personalized data is challenging due to privacy concerns and technical difficulties in recording audio from the test scene. To address these issues, synthetic data generation using generative models has gained significant attention. In this challenge, participants are tasked first with building zero-shot TTS systems to augment personalized data. Subsequently, PSE systems are asked to be trained with this augmented personalized dataset. Through this challenge, we aim to investigate how the quality of augmented data generated by zero-shot TTS models affects PSE model performance. We also provide baseline experiments using open-source zero-shot TTS models to encourage participation and benchmark advancements. Our baseline code implementation and checkpoints are available online.
KW - generative data augmentation
KW - personalized speech enhancement
KW - Zero-shot speech synthesis
UR - https://www.scopus.com/pages/publications/105007707203
UR - https://www.scopus.com/inward/citedby.url?scp=105007707203&partnerID=8YFLogxK
U2 - 10.1109/ICASSPW65056.2025.11011159
DO - 10.1109/ICASSPW65056.2025.11011159
M3 - Conference contribution
AN - SCOPUS:105007707203
T3 - 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2025 - Workshop Proceedings
BT - 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2025 - Workshop Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 April 2025 through 11 April 2025
ER -