# FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

arXiv: https://arxiv.org/abs/2006.04558 · HTML: https://mlsanity.com/paper/2006.04558/

## Key facts

- Cited by 717 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 30 of 717)

- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [AudioGen: Textually Guided Audio Generation](https://mlsanity.com/paper/2209.15352/) (2022)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [Diff-TTS: A Denoising Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2104.01409/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality](https://mlsanity.com/paper/2205.04421/) (2022)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [Matcha-TTS: A fast TTS architecture with conditional flow matching](https://mlsanity.com/paper/2309.03199/) (2023)
- [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](https://mlsanity.com/paper/2204.09934/) (2022)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Textless Speech-to-Speech Translation on Real Data](https://mlsanity.com/paper/2112.08352/) (2021)
- [Systematic Inequalities in Language Technology Performance across the World's Languages](https://mlsanity.com/paper/2110.06733/) (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)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [Textually Pretrained Speech Language Models](https://mlsanity.com/paper/2305.13009/) (2023)

## Abstract (arXiv)

Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at https://speechresearch.github.io/fastspeech2/.