# Latent Filling: Latent Space Data Augmentation for Zero-shot Speech Synthesis

arXiv: https://arxiv.org/abs/2310.03538 · HTML: https://mlsanity.com/paper/2310.03538/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2023.

## Built on by (most cited first, 4 of 4)

- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement](https://mlsanity.com/paper/2501.13372/) (2025)
- [Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition](https://mlsanity.com/paper/2511.20534/) (2025)
- [Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains](https://mlsanity.com/paper/2602.02841/) (2026)

## Abstract (arXiv)

Previous works in zero-shot text-to-speech (ZS-TTS) have attempted to enhance its systems by enlarging the training data through crowd-sourcing or augmenting existing speech data. However, the use of low-quality data has led to a decline in the overall system performance. To avoid such degradation, instead of directly augmenting the input data, we propose a latent filling (LF) method that adopts simple but effective latent space data augmentation in the speaker embedding space of the ZS-TTS system. By incorporating a consistency loss, LF can be seamlessly integrated into existing ZS-TTS systems without the need for additional training stages. Experimental results show that LF significantly improves speaker similarity while preserving speech quality.