# A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis

arXiv: https://arxiv.org/abs/2203.11562 · HTML: https://mlsanity.com/paper/2203.11562/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 67 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 30 of 31)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search](https://mlsanity.com/paper/2005.11129/) (2020)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Deep Voice 2: Multi-Speaker Neural Text-to-Speech](https://mlsanity.com/paper/1705.08947/) (2017)
- [Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings](https://mlsanity.com/paper/1910.10838/) (2019)
- [Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling](https://mlsanity.com/paper/2010.04301/) (2020)
- [Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens](https://mlsanity.com/paper/1910.11997/) (2019)
- [LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition](https://mlsanity.com/paper/2008.03687/) (2020)
- [MultiSpeech: Multi-Speaker Text to Speech with Transformer](https://mlsanity.com/paper/2006.04664/) (2020)
- [An Open source Implementation of ITU-T Recommendation P.808 with Validation](https://mlsanity.com/paper/2005.08138/) (2020)
- [From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint](https://mlsanity.com/paper/2005.04587/) (2020)
- [Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions](https://mlsanity.com/paper/2008.05289/) (2020)
- [Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?](https://mlsanity.com/paper/2005.01245/) (2020)
- [Fundamental Frequency Feature Normalization and Data Augmentation for Child Speech Recognition](https://mlsanity.com/paper/2102.09106/) (2021)
- [Towards Robust Neural Vocoding for Speech Generation: A Survey](https://mlsanity.com/paper/1912.02461/) (2019)
- [The NTNU System at the Interspeech 2020 Non-Native Children's Speech ASR Challenge](https://mlsanity.com/paper/2005.08433/) (2020)
- [High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling](https://mlsanity.com/paper/2105.09856/) (2021)

## Built on by (most cited first, 5 of 5)

- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?](https://mlsanity.com/paper/2508.21225/) (2025)
- [Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning](https://mlsanity.com/paper/2311.04313/) (2023)
- [Synthetic Speaking Children -- Why We Need Them and How to Make Them](https://mlsanity.com/paper/2311.06307/) (2023)
- [From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles](https://mlsanity.com/paper/2605.06439/) (2026)

## Abstract (arXiv)

Speech synthesis has come a long way as current text-to-speech (TTS) models can now generate natural human-sounding speech. However, most of the TTS research focuses on using adult speech data and there has been very limited work done on child speech synthesis. This study developed and validated a training pipeline for fine-tuning state-of-the-art (SOTA) neural TTS models using child speech datasets. This approach adopts a multi-speaker TTS retuning workflow to provide a transfer-learning pipeline. A publicly available child speech dataset was cleaned to provide a smaller subset of approximately 19 hours, which formed the basis of our fine-tuning experiments. Both subjective and objective evaluations were performed using a pretrained MOSNet for objective evaluation and a novel subjective framework for mean opinion score (MOS) evaluations. Subjective evaluations achieved the MOS of 3.95 for speech intelligibility, 3.89 for voice naturalness, and 3.96 for voice consistency. Objective evaluation using a pretrained MOSNet showed a strong correlation between real and synthetic child voices. Speaker similarity was also verified by calculating the cosine similarity between the embeddings of utterances. An automatic speech recognition (ASR) model is also used to provide a word error rate (WER) comparison between the real and synthetic child voices. The final trained TTS model was able to synthesize child-like speech from reference audio samples as short as 5 seconds.