# Diffusion Language Models for Speech Recognition

arXiv: https://arxiv.org/abs/2604.14001 · HTML: https://mlsanity.com/paper/2604.14001/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 27 of 27)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [A Continuous Time Framework for Discrete Denoising Models](https://mlsanity.com/paper/2205.14987/) (2022)
- [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025)
- [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://mlsanity.com/paper/2506.20639/) (2025)
- [The Diffusion Duality](https://mlsanity.com/paper/2506.10892/) (2025)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Language Modeling with Deep Transformers](https://mlsanity.com/paper/1905.04226/) (2019)
- [Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2011.01991/) (2020)
- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)
- [A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition](https://mlsanity.com/paper/1807.10857/) (2018)
- [Diffusion Beats Autoregressive in Data-Constrained Settings](https://mlsanity.com/paper/2507.15857/) (2025)
- [Diffusion Language Models are Super Data Learners](https://mlsanity.com/paper/2511.03276/) (2025)
- [Non-Autoregressive Text Generation with Pre-trained Language Models](https://mlsanity.com/paper/2102.08220/) (2021)
- [Scaling Behavior of Discrete Diffusion Language Models](https://mlsanity.com/paper/2512.10858/) (2025)
- [A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation](https://mlsanity.com/paper/2110.05249/) (2021)
- [Scaling Beyond Masked Diffusion Language Models](https://mlsanity.com/paper/2602.15014/) (2026)
- [Librispeech Transducer Model with Internal Language Model Prior Correction](https://mlsanity.com/paper/2104.03006/) (2021)
- [Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models](https://mlsanity.com/paper/2201.10103/) (2022)
- [The Diffusion Duality, Chapter II: Psi-Samplers](https://mlsanity.com/paper/2602.21185/) (2026)
- [Revisiting ASR Error Correction with Specialized Models](https://mlsanity.com/paper/2405.15216/) (2024)
- [Drax: Speech Recognition with Discrete Flow Matching](https://mlsanity.com/paper/2510.04162/) (2025)
- [dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition](https://mlsanity.com/paper/2601.17902/) (2026)
- [Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing](https://mlsanity.com/paper/2509.16622/) (2025)

## Abstract (arXiv)

Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide to incorporating masked diffusion language models (MDLM) and uniform-state diffusion models (USDMs) for rescoring ASR hypotheses. Additionally, we design a new joint-decoding method that combines CTC and USDM by integrating the framewise probability distributions derived from CTC with the labelwise probability distributions computed by USDM at each decoding step, thereby generating new candidates that combine strong language knowledge from USDM and acoustic information from CTC. Our findings reveal that USDM, as well as MDLM, can significantly improve the accuracy of recognized text. We publish all our code and recipes.