# dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition

arXiv: https://arxiv.org/abs/2601.17902 · HTML: https://mlsanity.com/paper/2601.17902/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2026.

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

- [LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation](https://mlsanity.com/paper/2604.11052/) (2026)
- [Diffusion Language Models for Speech Recognition](https://mlsanity.com/paper/2604.14001/) (2026)

## Abstract (arXiv)

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows linearly with sequence length. Meanwhile, discrete diffusion large language models (dLLMs) offer a promising alternative, enabling high-quality parallel sequence generation with pretrained decoders. However, directly applying native text-oriented dLLMs to ASR leads to a fundamental mismatch between open-ended text generation and the acoustically conditioned transcription paradigm required by ASR. As a result, it introduces unnecessary difficulty and computational redundancy, such as denoising from pure noise, inflexible generation lengths, and fixed denoising steps. We propose dLLM-ASR, an efficient dLLM-based ASR framework that formulates dLLM's decoding as a prior-guided and adaptive denoising process. It leverages an ASR prior to initialize the denoising process and provide an anchor for sequence length. Building upon this prior, length-adaptive pruning dynamically removes redundant tokens, while confidence-based denoising allows converged tokens to exit the denoising loop early, enabling token-level adaptive computation. Experiments demonstrate that dLLM-ASR achieves recognition accuracy comparable to autoregressive LLM-based ASR systems and delivers a 4.44× inference speedup, establishing a practical and efficient paradigm for ASR.