# FastPitch: Parallel Text-to-speech with Pitch Prediction

arXiv: https://arxiv.org/abs/2006.06873 · HTML: https://mlsanity.com/paper/2006.06873/

## Key facts

- Cited by 151 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 151)

- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Diff-TTS: A Denoising Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2104.01409/) (2021)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [Text-Free Prosody-Aware Generative Spoken Language Modeling](https://mlsanity.com/paper/2109.03264/) (2021)
- [Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation](https://mlsanity.com/paper/2106.03153/) (2021)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [One TTS Alignment To Rule Them All](https://mlsanity.com/paper/2108.10447/) (2021)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis](https://mlsanity.com/paper/2205.15439/) (2022)
- [Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation](https://mlsanity.com/paper/2311.04693/) (2023)
- [EdiTTS: Score-based Editing for Controllable Text-to-Speech](https://mlsanity.com/paper/2110.02584/) (2021)
- [Towards Building Text-To-Speech Systems for the Next Billion Users](https://mlsanity.com/paper/2211.09536/) (2022)
- [JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech](https://mlsanity.com/paper/2203.16852/) (2022)
- [Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2412.06602/) (2024)
- [ESPnet2-TTS: Extending the Edge of TTS Research](https://mlsanity.com/paper/2110.07840/) (2021)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features](https://mlsanity.com/paper/2203.03191/) (2022)
- [DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset](https://mlsanity.com/paper/2409.08731/) (2024)
- [GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis](https://mlsanity.com/paper/2106.15153/) (2021)
- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [WavThruVec: Latent speech representation as intermediate features for neural speech synthesis](https://mlsanity.com/paper/2203.16930/) (2022)
- [DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training](https://mlsanity.com/paper/2307.16549/) (2023)
- [Low-Resource Multilingual and Zero-Shot Multispeaker TTS](https://mlsanity.com/paper/2210.12223/) (2022)
- [ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations](https://mlsanity.com/paper/2302.08137/) (2023)
- [TTSDS -- Text-to-Speech Distribution Score](https://mlsanity.com/paper/2407.12707/) (2024)
- [Context-Aware Prosody Correction for Text-Based Speech Editing](https://mlsanity.com/paper/2102.08328/) (2021)
- [Heterogeneous Target Speech Separation](https://mlsanity.com/paper/2204.03594/) (2022)

## Abstract (arXiv)

We present FastPitch, a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be more expressive, better match the semantic of the utterance, and in the end more engaging to the listener. Uniformly increasing or decreasing pitch with FastPitch generates speech that resembles the voluntary modulation of voice. Conditioning on frequency contours improves the overall quality of synthesized speech, making it comparable to state-of-the-art. It does not introduce an overhead, and FastPitch retains the favorable, fully-parallel Transformer architecture, with over 900x real-time factor for mel-spectrogram synthesis of a typical utterance.