MLLM-based Speech Recognition: When and How is Multimodality Beneficial?

• URL: http://arxiv.org/abs/2507.19037v1
• Date: Fri, 25 Jul 2025 07:46:40 GMT
• Title: MLLM-based Speech Recognition: When and How is Multimodality Beneficial?
• Authors: Yiwen Guan, Viet Anh Trinh, Vivek Voleti, Jacob Whitehill,
• Abstract summary: Multi-modal large language models (MLLMs) have opened new possibilities for unified modeling of speech, text, images, and other modalities.<n>This paper examines the conditions and model architectures under which multiple input modalities can improve automatic speech recognition (ASR) accuracy in noisy environments.
• Score: 12.662031101992968
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in multi-modal large language models (MLLMs) have opened new possibilities for unified modeling of speech, text, images, and other modalities. Building on our prior work, this paper examines the conditions and model architectures under which multiple input modalities can improve automatic speech recognition (ASR) accuracy in noisy environments. Through experiments on synthetic and real-world data, we find that (1) harnessing more modalities usually improves ASR accuracy, as each modality provides complementary information, but the improvement depends on the amount of auditory noise. (2) Synchronized modalities (e.g., lip movements) are more useful at high noise levels whereas unsynchronized modalities (e.g., image context) are most helpful at moderate noise levels. (3) Higher-quality visual representations consistently improve ASR accuracy, highlighting the importance of developing more powerful visual encoders. (4) Mamba exhibits similar trends regarding the benefits of multimodality as do Transformers. (5) The input order of modalities as well as their weights in the loss function can significantly impact accuracy. These findings both offer practical insights and help to deepen our understanding of multi-modal speech recognition under challenging conditions.

Related papers

• AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection [57.649223695021114]
  We present a novel weakly supervised framework that leverages audio-visual collaboration for robust video anomaly detection.<n>Our framework demonstrates superior performance across multiple benchmarks, with audio integration significantly boosting anomaly detection accuracy.
  arXiv  Detail & Related papers  (2025-04-06T13:59:16Z)
• R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning [11.614909833431808]
  We present the first application of Reinforcement Learning with Verifiable Reward (RLVR) to an Omni-multimodal large language model in the context of emotion recognition.<n>We leverage RLVR to optimize the Omni model, significantly enhancing its performance in three key aspects: reasoning capability, emotion recognition accuracy, and generalization ability.
  arXiv  Detail & Related papers  (2025-03-07T12:46:42Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition [57.131546757903834]
  Lyra is an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction.<n>Lyra achieves state-of-the-art performance on various vision-language, vision-speech, and speech-language benchmarks, while also using fewer computational resources and less training data.
  arXiv  Detail & Related papers  (2024-12-12T17:50:39Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• OmniBench: Towards The Future of Universal Omni-Language Models [63.16606414452612]
  We introduce OmniBench, a novel benchmark designed to evaluate models' ability to recognize, interpret, and reason across visual, acoustic, and textual inputs simultaneously.<n>Our evaluation reveals that open-source OLMs show significant limitations in instruction-following and reasoning in tri-modal contexts.<n>We advocate for developing more robust tri-modal integration techniques and training strategies to enhance OLM performance.
  arXiv  Detail & Related papers  (2024-09-23T17:59:05Z)
• Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy? [12.662031101992968]
  We investigate the effects of multiple modalities on recognition accuracy on both synthetic and real-world datasets.<n>Images as a supplementary modality for speech recognition provide the greatest benefit at moderate noise levels.<n>Performance improves on both synthetic and real-world datasets when the most relevant visual information is filtered as a preprocessing step.
  arXiv  Detail & Related papers  (2024-09-13T22:18:45Z)
• Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning [25.743503223389784]
  We propose a reinforcement learning (RL) based framework called MSRL. We customize a reward function directly related to task-specific metrics. Experimental results on the LRS3 dataset show that the proposed method achieves state-of-the-art in both clean and various noisy conditions.
  arXiv  Detail & Related papers  (2022-12-10T14:01:54Z)
• Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation [32.68710772281511]
  We present a self-supervised framework for audio-visual representation learning, to localize the sound source in videos. Our model significantly outperforms previous methods on two sound localization benchmarks, namely, Flickr-SoundNet and VGG-Sound. This reveals the proposed framework learns strong multi-modal representations that are beneficial to sound localisation and generalization to further applications.
  arXiv  Detail & Related papers  (2022-06-26T03:00:02Z)
• High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning [112.51498431119616]
  This paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. A single model, HighMMT, scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas.
  arXiv  Detail & Related papers  (2022-03-02T18:56:20Z)
• Discriminative Multi-modality Speech Recognition [17.296404414250553]
  Vision is often used as a complementary modality for audio speech recognition (ASR) In this paper, we propose a two-stage speech recognition model. In the first stage, the target voice is separated from background noises with help from the corresponding visual information of lip movements, making the model 'listen' clearly. At the second stage, the audio modality combines visual modality again to better understand the speech by a MSR sub-network, further improving the recognition rate.
  arXiv  Detail & Related papers  (2020-05-12T07:56:03Z)
• Mutual Information Maximization for Effective Lip Reading [99.11600901751673]
  We propose to introduce the mutual information constraints on both the local feature's level and the global sequence's level. By combining these two advantages together, the proposed method is expected to be both discriminative and robust for effective lip reading.
  arXiv  Detail & Related papers  (2020-03-13T18:47:42Z)

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.