# Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings

arXiv: https://arxiv.org/abs/2110.03584 · HTML: https://mlsanity.com/paper/2110.03584/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2021.

## Built on by (most cited first, 8 of 8)

- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs](https://mlsanity.com/paper/2203.03990/) (2022)
- [Transformer-Based Speech Synthesizer Attribution in an Open Set Scenario](https://mlsanity.com/paper/2210.07546/) (2022)
- [EfficientSpeech: An On-Device Text to Speech Model](https://mlsanity.com/paper/2305.13905/) (2023)
- [DC CoMix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer](https://mlsanity.com/paper/2305.19567/) (2023)
- [RWEN-TTS: Relation-aware Word Encoding Network for Natural Text-to-Speech Synthesis](https://mlsanity.com/paper/2212.07939/) (2022)
- [Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners](https://mlsanity.com/paper/2302.14523/) (2023)
- [GrainSpeech: Less Context, More Detail for Compact Speech Synthesis](https://mlsanity.com/paper/2609.18856/) (2026)

## Abstract (arXiv)

This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic Mixer-TTS contains pitch and duration predictors, with the latter being trained with an unsupervised TTS alignment framework. Alongside the basic model, we propose the extended version which additionally uses token embeddings from a pre-trained language model. Basic Mixer-TTS and its extended version achieve a mean opinion score (MOS) of 4.05 and 4.11, respectively, compared to a MOS of 4.27 of original LJSpeech samples. Both versions have a small number of parameters and enable much faster speech synthesis compared to the models with similar quality.