# AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment

arXiv: https://arxiv.org/abs/2003.01950 · HTML: https://mlsanity.com/paper/2003.01950/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 20 of 20)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs](https://mlsanity.com/paper/2201.11972/) (2022)
- [SpeechNet: A Universal Modularized Model for Speech Processing Tasks](https://mlsanity.com/paper/2105.03070/) (2021)
- [Federated Learning with Dynamic Transformer for Text to Speech](https://mlsanity.com/paper/2107.08795/) (2021)
- [Neural HMMs are all you need (for high-quality attention-free TTS)](https://mlsanity.com/paper/2108.13320/) (2021)
- [Review of end-to-end speech synthesis technology based on deep learning](https://mlsanity.com/paper/2104.09995/) (2021)
- [Fast DCTTS: Efficient Deep Convolutional Text-to-Speech](https://mlsanity.com/paper/2104.00624/) (2021)
- [Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss](https://mlsanity.com/paper/2204.13437/) (2022)
- [Marco-Voice Technical Report](https://mlsanity.com/paper/2508.02038/) (2025)
- [Semi-Supervised Learning Based on Reference Model for Low-resource TTS](https://mlsanity.com/paper/2210.14723/) (2022)
- [UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control](https://mlsanity.com/paper/2106.11171/) (2021)
- [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)
- [MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces](https://mlsanity.com/paper/2402.12845/) (2024)
- [Eliminating stability hallucinations in llm-based tts models via attention guidance](https://mlsanity.com/paper/2509.19852/) (2025)
- [AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs](https://mlsanity.com/paper/2511.21251/) (2025)
- [Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprache](https://mlsanity.com/paper/2106.06230/) (2021)
- [Multi-Scale Spectrogram Modelling for Neural Text-to-Speech](https://mlsanity.com/paper/2106.15649/) (2021)
- [PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control](https://mlsanity.com/paper/2110.04486/) (2021)
- [AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling](https://mlsanity.com/paper/2203.11049/) (2022)

## Abstract (arXiv)

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of each character is determined by a duration predictor.Instead of adopting the attention mechanism in Transformer TTS to align text to mel-spectrum, the alignment loss is presented to consider all possible alignments in training by use of dynamic programming. Experiments on the LJSpeech dataset show that our model achieves not only state-of-the-art performance which outperforms Transformer TTS by 0.03 in mean option score (MOS), but also a high efficiency which is more than 50 times faster than real-time.