# EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture

arXiv: https://arxiv.org/abs/2012.03500 · HTML: https://mlsanity.com/paper/2012.03500/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 14 of 14)

- [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)
- [A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI](https://mlsanity.com/paper/2303.13336/) (2023)
- [DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs](https://mlsanity.com/paper/2201.11972/) (2022)
- [StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis](https://mlsanity.com/paper/2205.15439/) (2022)
- [JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech](https://mlsanity.com/paper/2203.16852/) (2022)
- [OverFlow: Putting flows on top of neural transducers for better TTS](https://mlsanity.com/paper/2211.06892/) (2022)
- [Pheme: Efficient and Conversational Speech Generation](https://mlsanity.com/paper/2401.02839/) (2024)
- [Improving Generalization for AI-Synthesized Voice Detection](https://mlsanity.com/paper/2412.19279/) (2024)
- [UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts](https://mlsanity.com/paper/2404.18398/) (2024)
- [On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis](https://mlsanity.com/paper/2110.01147/) (2021)
- [Cross-Utterance Conditioned VAE for Speech Generation](https://mlsanity.com/paper/2309.04156/) (2023)
- [HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks](https://mlsanity.com/paper/2404.04645/) (2024)
- [AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling](https://mlsanity.com/paper/2203.11049/) (2022)

## Abstract (arXiv)

In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS optimizes all its parameters with a stable, end-to-end training procedure, while allowing for synthesizing high quality speech in a fast and efficient manner. EfficientTTS is motivated by a new monotonic alignment modeling approach (also introduced in this work), which specifies monotonic constraints to the sequence alignment with almost no increase of computation. By combining EfficientTTS with different feed-forward network structures, we develop a family of TTS models, including both text-to-melspectrogram and text-to-waveform networks. We experimentally show that the proposed models significantly outperform counterpart models such as Tacotron 2 and Glow-TTS in terms of speech quality, training efficiency and synthesis speed, while still producing the speeches of strong robustness and great diversity. In addition, we demonstrate that proposed approach can be easily extended to autoregressive models such as Tacotron 2.