Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing

• URL: http://arxiv.org/abs/2509.16622v2
• Date: Thu, 09 Oct 2025 07:55:28 GMT
• Title: Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
• Authors: Mengqi Wang, Zhan Liu, Zengrui Jin, Guangzhi Sun, Chao Zhang, Philip C. Woodland,
• Abstract summary: We present an empirical study on using the diffusion-based large language model LLaDA for automatic speech recognition (ASR)<n>We explore random masking, low-confidence masking, and semi-autoregressive strategies, showing that Whisper-LLaDA substantially reduces WER compared with the baseline.<n>Most experimental configurations achieve faster inference than the Whisper-LLaMA baseline, although recognition accuracy is slightly lower.
• Score: 33.36615989947073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for automatic speech recognition (ASR). We first investigate its use as an external deliberation-based processing module for Whisper-LLaMA transcripts. By leveraging the bidirectional attention and denoising capabilities of LLaDA, we explore random masking, low-confidence masking, and semi-autoregressive strategies, showing that Whisper-LLaDA substantially reduces WER compared with the baseline. On LibriSpeech, the best cascade system achieves 2.25%/4.94% WER on test-clean/test-other, representing a 12.3% relative improvement over the Whisper-LLaMA baseline on the test-other split. In contrast, a plain-text LLaDA without acoustic features fails to improve accuracy, highlighting the importance of audio-conditioned embeddings. We further evaluate Whisper-LLaDA as a standalone decoder for ASR with diffusion-based and semi-autoregressive decoding. Most experimental configurations achieve faster inference than the Whisper-LLaMA baseline, although recognition accuracy is slightly lower. These findings offer an empirical view of diffusion-based LLMs for ASR and point to promising directions for improvements.

Related papers

• Speech Emotion Recognition Leveraging OpenAI's Whisper Representations and Attentive Pooling Methods [0.15749416770494704]
  Speech Emotion Recognition (SER) research has faced limitations due to the lack of standard and sufficiently large datasets.<n>Recent studies have leveraged pre-trained models to extract features for downstream tasks such as SER.<n>This work explores the capabilities of Whisper, a pre-trained ASR system, in speech emotion recognition.
  arXiv  Detail & Related papers  (2026-02-05T18:46:28Z)
• SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models [49.313324100819955]
  Signal Embedding Energy (SEE) is a method for quantifying the impact of noise intensity on LALM inputs.<n>SEE exhibits a strong correlation with LALM performance, achieving a correlation of 0.98.<n>This paper introduces a novel metric for noise quantification in LALMs, providing guidance for robustness improvements in real-world deployments.
  arXiv  Detail & Related papers  (2026-01-12T08:57:55Z)
• Reproducing and Dissecting Denoising Language Models for Speech Recognition [31.91567892562116]
  Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR)<n>This paper presents the first independent, large-scale empirical study of DLMs.
  arXiv  Detail & Related papers  (2025-12-15T17:33:22Z)
• MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization [66.82303841930752]
  diffusion language models (DLMs) have presented a promising alternative to traditional autoregressive large language models (LLMs)<n>DLMs still lag behind LLMs in reasoning performance, especially as the number of denoising steps decreases.<n>We propose a Multi-Reward Optimization (MRO) approach, which encourages DLMs to consider the token correlation during the denoising process.
  arXiv  Detail & Related papers  (2025-10-24T13:57:59Z)
• Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses [71.34350093068473]
  This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR)<n>Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models.<n>Our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain.
  arXiv  Detail & Related papers  (2025-10-15T08:27:16Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs [33.12165044958361]
  Recent advances in Large Language Models (LLMs) show strong performance in speech recognition, including Audio-Visual Speech Recognition (AVSR)<n>To address this, we propose Llama-MTSK, the first Matryoshka-based Multimodal LLM for AVSR.<n>Inspired by Matryoshka Representation Learning, our model encodes representations at multiple granularities with a single architecture.<n>For efficient fine-tuning, we introduce three LoRA-based strategies using global and scale-specific modules.
  arXiv  Detail & Related papers  (2025-03-09T00:02:10Z)
• Large Language Models are Strong Audio-Visual Speech Recognition Learners [53.142635674428874]
  Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities.<n>We propose Llama-AVSR, a new MLLM with strong audio-visual speech recognition capabilities.<n>We evaluate our proposed approach on LRS3, the largest public AVSR benchmark, and we achieve new state-of-the-art results for the tasks of ASR and AVSR with a WER of 0.79% and 0.77%, respectively.
  arXiv  Detail & Related papers  (2024-09-18T21:17:27Z)
• LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition [46.438575751932866]
  LipGER is a framework for leveraging visual cues for noise-robust ASR. We show that LipGER improves the Word Error Rate in the range of 1.1%-49.2%. We also release LipHyp, a large-scale dataset with hypothesis-transcription pairs equipped with lip motion cues.
  arXiv  Detail & Related papers  (2024-06-06T18:17:59Z)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition [70.77292069313154]
  Large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. In this work, we aim to overcome such a limitation by infusing acoustic information before generating the predicted transcription through a novel late fusion solution termed Uncertainty-Aware Dynamic Fusion (UADF)
  arXiv  Detail & Related papers  (2024-02-08T07:21:45Z)
• DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification [55.306583814017046]
  We present a novel difficulty-aware semantic augmentation (DASA) approach for speaker verification. DASA generates diversified training samples in speaker embedding space with negligible extra computing cost. The best result achieves a 14.6% relative reduction in EER metric on CN-Celeb evaluation set.
  arXiv  Detail & Related papers  (2023-10-18T17:07:05Z)
• Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation [83.36685075570232]
  This work provides an insightful investigation of speech separation in reverberant and noisy-reverberant scenarios as an ASR front-end. We explore multi-channel separation methods, mask-based beamforming and complex spectral mapping, as well as the best features to use in the ASR back-end model. A proposed integration using TF-GridNet-based complex spectral mapping and WavLM-based SSLR achieves a 2.5% word error rate in reverberant WHAMR! test set.
  arXiv  Detail & Related papers  (2023-07-23T05:39:39Z)
• Cross-Utterance Language Models with Acoustic Error Sampling [1.376408511310322]
  Cross-utterance LM (CULM) is proposed to augment the input to a standard long short-term memory (LSTM) LM. An acoustic error sampling technique is proposed to reduce the mismatch between training and test-time. Experiments performed on both AMI and Switchboard datasets show that CULMs outperform the LSTM LM baseline WER.
  arXiv  Detail & Related papers  (2020-08-19T17:40:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.