Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement

TL;DR

This paper introduces a challenge for zero-shot text-to-speech systems to generate synthetic personalized speech data, aiming to improve personalized speech enhancement while addressing data privacy and collection difficulties.

Contribution

It proposes a new challenge framework for using zero-shot TTS to augment data for PSE, including baseline models and benchmarks to foster research progress.

Findings

Baseline zero-shot TTS models impact PSE performance

Synthetic data quality influences speech enhancement effectiveness

Open-source benchmarks provided for community participation

Abstract

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.