# Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?

arXiv: https://arxiv.org/abs/2005.01245 · HTML: https://mlsanity.com/paper/2005.01245/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 9 of 9)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks](https://mlsanity.com/paper/2203.14156/) (2022)
- [A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis](https://mlsanity.com/paper/2203.11562/) (2022)
- [Combining speakers of multiple languages to improve quality of neural voices](https://mlsanity.com/paper/2108.07737/) (2021)
- [Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control](https://mlsanity.com/paper/2111.10168/) (2021)
- [Controllable speech synthesis by learning discrete phoneme-level prosodic representations](https://mlsanity.com/paper/2211.16307/) (2022)
- [Data-augmented cross-lingual synthesis in a teacher-student framework](https://mlsanity.com/paper/2204.00061/) (2022)
- [Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning](https://mlsanity.com/paper/2311.04313/) (2023)
- [Code-Mixed Text to Speech Synthesis under Low-Resource Constraints](https://mlsanity.com/paper/2312.01103/) (2023)

## Abstract (arXiv)

Previous work on speaker adaptation for end-to-end speech synthesis still falls short in speaker similarity. We investigate an orthogonal approach to the current speaker adaptation paradigms, speaker augmentation, by creating artificial speakers and by taking advantage of low-quality data. The base Tacotron2 model is modified to account for the channel and dialect factors inherent in these corpora. In addition, we describe a warm-start training strategy that we adopted for Tacotron2 training. A large-scale listening test is conducted, and a distance metric is adopted to evaluate synthesis of dialects. This is followed by an analysis on synthesis quality, speaker and dialect similarity, and a remark on the effectiveness of our speaker augmentation approach. Audio samples are available online.