# BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing

arXiv: https://arxiv.org/abs/2506.03515 · HTML: https://mlsanity.com/paper/2506.03515/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [An Exponential Learning Rate Schedule for Deep Learning](https://mlsanity.com/paper/1910.07454/) (2019)
- [LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus](https://mlsanity.com/paper/2305.18802/) (2023)
- [XNOR-Net++: Improved Binary Neural Networks](https://mlsanity.com/paper/1909.13863/) (2019)
- [ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech](https://mlsanity.com/paper/1807.07281/) (2018)
- [ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit](https://mlsanity.com/paper/1910.10909/) (2019)
- [A Review of Deep Learning Techniques for Speech Processing](https://mlsanity.com/paper/2305.00359/) (2023)
- [An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era](https://mlsanity.com/paper/2210.03538/) (2022)
- [LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search](https://mlsanity.com/paper/2102.04040/) (2021)
- [JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech](https://mlsanity.com/paper/2203.16852/) (2022)
- [4-bit Conformer with Native Quantization Aware Training for Speech Recognition](https://mlsanity.com/paper/2203.15952/) (2022)
- [Basic Binary Convolution Unit for Binarized Image Restoration Network](https://mlsanity.com/paper/2210.00405/) (2022)
- [SpeedySpeech: Efficient Neural Speech Synthesis](https://mlsanity.com/paper/2008.03802/) (2020)
- [Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis](https://mlsanity.com/paper/2105.13086/) (2021)
- [2-bit Conformer quantization for automatic speech recognition](https://mlsanity.com/paper/2305.16619/) (2023)
- [Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform](https://mlsanity.com/paper/2210.15975/) (2022)
- [Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition](https://mlsanity.com/paper/2206.15408/) (2022)

## Built on by (most cited first, 2 of 2)

- [Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models](https://mlsanity.com/paper/2603.08173/) (2026)
- [Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures](https://mlsanity.com/paper/2609.28974/) (2026)

## Abstract (arXiv)

This paper proposes a highly compact, lightweight text-to-speech (TTS) model for on-device applications. To reduce the model size, the proposed model introduces two techniques. First, we introduce quantization-aware training (QAT), which quantizes model parameters during training to as low as 1.58-bit. In this case, most of 32-bit model parameters are quantized to ternary values {-1, 0, 1}. Second, we propose a method named weight indexing. In this method, we save a group of 1.58-bit weights as a single int8 index. This allows for efficient storage of model parameters, even on hardware that treats values in units of 8-bit. Experimental results demonstrate that the proposed method achieved 83 % reduction in model size, while outperforming the baseline of similar model size without quantization in synthesis quality.