# Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model

arXiv: https://arxiv.org/abs/2607.13013 · HTML: https://mlsanity.com/paper/2607.13013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 14 Jul 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models](https://mlsanity.com/paper/2210.08933/) (2022)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [Whisfusion: Parallel ASR Decoding with Masked Diffusion](https://mlsanity.com/paper/2508.07048/) (2025)

## Built on by (most cited first, 1 of 1)

- [Full-duplex Spoken Language Modeling with Discrete Diffusion](https://mlsanity.com/paper/2610.17780/) (2026)

## Abstract (arXiv)

Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for DiffusionGemma, a 26B mixture-of-experts model that generates text by uniform, random-token discrete diffusion rather than the absorbing-mask scheme common to recent diffusion language models. A frozen Whisper encoder supplies acoustic features, a lightweight projector maps them into the model embedding space, and low-rank adapters let the frozen backbone attend to the new modality. About 42M parameters are trained, which is 0.16 percent of the backbone. We find that the natural training objectives fail to ground the audio because their gradient reaches the projector only through attention that has already dismissed it. A connectionist temporal classification loss applied through the frozen output head breaks this deadlock. The resulting model reaches 6.6 percent word error rate on LibriSpeech test-clean, transcribes in roughly eight parallel steps regardless of utterance length, and uses a single adapter trained on six languages, which we evaluate here on English, Hindi, and Mandarin.