# Non-Autoregressive Neural Text-to-Speech

arXiv: https://arxiv.org/abs/1905.08459 · HTML: https://mlsanity.com/paper/1905.08459/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

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

- [A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing](https://mlsanity.com/paper/2203.09690/) (2022)
- [LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search](https://mlsanity.com/paper/2102.04040/) (2021)
- [High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency](https://mlsanity.com/paper/2111.09052/) (2021)
- [Non-autoregressive sequence-to-sequence voice conversion](https://mlsanity.com/paper/2104.06793/) (2021)
- [TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction](https://mlsanity.com/paper/2104.08189/) (2021)
- [A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS](https://mlsanity.com/paper/2212.03817/) (2022)
- [Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech](https://mlsanity.com/paper/2205.04120/) (2022)
- [Cross-Utterance Conditioned VAE for Speech Generation](https://mlsanity.com/paper/2309.04156/) (2023)
- [Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction](https://mlsanity.com/paper/2505.18731/) (2025)

## Abstract (arXiv)

In this work, we propose ParaNet, a non-autoregressive seq2seq model that converts text to spectrogram. It is fully convolutional and brings 46.7 times speed-up over the lightweight Deep Voice 3 at synthesis, while obtaining reasonably good speech quality. ParaNet also produces stable alignment between text and speech on the challenging test sentences by iteratively improving the attention in a layer-by-layer manner. Furthermore, we build the parallel text-to-speech system and test various parallel neural vocoders, which can synthesize speech from text through a single feed-forward pass. We also explore a novel VAE-based approach to train the inverse autoregressive flow (IAF) based parallel vocoder from scratch, which avoids the need for distillation from a separately trained WaveNet as previous work.