# Adapitch: Adaption Multi-Speaker Text-to-Speech Conditioned on Pitch Disentangling with Untranscribed Data

arXiv: https://arxiv.org/abs/2210.13803 · HTML: https://mlsanity.com/paper/2210.13803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 12 of 12)

- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (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)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [Low-resource expressive text-to-speech using data augmentation](https://mlsanity.com/paper/2011.05707/) (2020)
- [AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning](https://mlsanity.com/paper/2202.10020/) (2022)
- [Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning](https://mlsanity.com/paper/1910.12729/) (2019)
- [nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-shot Multi-speaker Text-to-Speech](https://mlsanity.com/paper/2202.10712/) (2022)
- [TDASS: Target Domain Adaptation Speech Synthesis Framework for Multi-speaker Low-Resource TTS](https://mlsanity.com/paper/2205.11824/) (2022)
- [A Comparative Study of Pitch Extraction Algorithms on a Large Variety of Singing Sounds](https://mlsanity.com/paper/1912.12609/) (2019)
- [SUSing: SU-net for Singing Voice Synthesis](https://mlsanity.com/paper/2205.11841/) (2022)

## Abstract (arXiv)

In this paper, we proposed Adapitch, a multi-speaker TTS method that makes adaptation of the supervised module with untranscribed data. We design two self supervised modules to train the text encoder and mel decoder separately with untranscribed data to enhance the representation of text and mel. To better handle the prosody information in a synthesized voice, a supervised TTS module is designed conditioned on content disentangling of pitch, text, and speaker. The training phase was separated into two parts, pretrained and fixed the text encoder and mel decoder with unsupervised mode, then the supervised mode on the disentanglement of TTS. Experiment results show that the Adaptich achieved much better quality than baseline methods.