# SpeedySpeech: Efficient Neural Speech Synthesis

arXiv: https://arxiv.org/abs/2008.03802 · HTML: https://mlsanity.com/paper/2008.03802/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 15 of 15)

- [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)
- [LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2308.16569/) (2023)
- [Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus](https://mlsanity.com/paper/2203.15447/) (2022)
- [Review of end-to-end speech synthesis technology based on deep learning](https://mlsanity.com/paper/2104.09995/) (2021)
- [Nix-TTS: Lightweight and End-to-End Text-to-Speech via Module-wise Distillation](https://mlsanity.com/paper/2203.15643/) (2022)
- [Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario](https://mlsanity.com/paper/2210.07546/) (2022)
- [Voice Cloning: Comprehensive Survey](https://mlsanity.com/paper/2505.00579/) (2025)
- [Prosody Analysis of Audiobooks](https://mlsanity.com/paper/2310.06930/) (2023)
- [Lightweight Zero-shot Text-to-Speech with Mixture of Adapters](https://mlsanity.com/paper/2407.01291/) (2024)
- [BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing](https://mlsanity.com/paper/2506.03515/) (2025)
- [Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications](https://mlsanity.com/paper/2505.07701/) (2025)
- [Sprachsynthese -- State-of-the-Art in englischer und deutscher Sprache](https://mlsanity.com/paper/2106.06230/) (2021)
- [AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling](https://mlsanity.com/paper/2203.11049/) (2022)
- [GrainSpeech: Less Context, More Detail for Compact Speech Synthesis](https://mlsanity.com/paper/2609.18856/) (2026)

## Abstract (arXiv)

While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. We propose a student-teacher network capable of high-quality faster-than-real-time spectrogram synthesis, with low requirements on computational resources and fast training time. We show that self-attention layers are not necessary for generation of high quality audio. We utilize simple convolutional blocks with residual connections in both student and teacher networks and use only a single attention layer in the teacher model. Coupled with a MelGAN vocoder, our model's voice quality was rated significantly higher than Tacotron 2. Our model can be efficiently trained on a single GPU and can run in real time even on a CPU. We provide both our source code and audio samples in our GitHub repository.