Figure 2 - available via license: Creative Commons Zero 1.0
Content may be subject to copyright.
Source publication
In recent years, the field of image generation has been revolutionized by the application of autoregressive transformers and DDPMs. These approaches model the process of image generation as a step-wise probabilistic processes and leverage large amounts of compute and data to learn the image distribution. This methodology of improving performance ne...
Similar publications
Citations
... SpeechT5 is a pre-trained encoder-decoder model for various spoken language processing tasks, including its TTS application, which we use as a baseline. Finally, XTTS is a zero-shot TTS model built on Tortoise [30], which incorporates a decoder-only Transformer with some modifications to improve voice cloning and enable faster training and inference. ...
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.
