# Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision

arXiv: https://arxiv.org/abs/2505.21245 · HTML: https://mlsanity.com/paper/2505.21245/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2025.

## Built on by (most cited first, 3 of 3)

- [Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models](https://mlsanity.com/paper/2603.08173/) (2026)
- [Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection](https://mlsanity.com/paper/2605.03039/) (2026)
- [Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering](https://mlsanity.com/paper/2606.11836/) (2026)

## Abstract (arXiv)

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally resource-constrained applications. We propose novel approaches to perform extremely low-bit (i.e., 2-bit and 1-bit) quantization of Conformer automatic speech recognition systems using multiple precision model co-training, stochastic precision, and tensor-wise learnable scaling factors to alleviate quantization incurred performance loss. The proposed methods can achieve performance-lossless 2-bit and 1-bit quantization of Conformer ASR systems trained with the 300-hr Switchboard and 960-hr LibriSpeech corpus. Maximum overall performance-lossless compression ratios of 16.2 and 16.6 times are achieved without a statistically significant increase in the word error rate (WER) over the full precision baseline systems, respectively.