Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs

• URL: http://arxiv.org/abs/2503.06362v1
• Date: Sun, 09 Mar 2025 00:02:10 GMT
• Title: Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs
• Authors: Umberto Cappellazzo, Minsu Kim, Stavros Petridis,
• Abstract summary: Recent advancements in Large Language Models (LLMs) have demonstrated their effectiveness in speech recognition, including Audio-Visual Speech Recognition (AVSR)<n>Due to the significant length of speech representations, direct integration with LLMs imposes substantial computational costs.<n>We propose Llama-MTSK, the first Matryoshka-based Multimodal LLM for AVSR, which enables flexible adaptation of the audio-visual token allocation.
• Score: 33.12165044958361
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio-Visual Speech Recognition (AVSR) leverages both audio and visual modalities to enhance speech recognition robustness, particularly in noisy environments. Recent advancements in Large Language Models (LLMs) have demonstrated their effectiveness in speech recognition, including AVSR. However, due to the significant length of speech representations, direct integration with LLMs imposes substantial computational costs. Prior approaches address this by compressing speech representations before feeding them into LLMs. However, higher compression ratios often lead to performance degradation, necessitating a trade-off between computational efficiency and recognition accuracy. To address this challenge, we propose Llama-MTSK, the first Matryoshka-based Multimodal LLM for AVSR, which enables flexible adaptation of the audio-visual token allocation based on specific computational constraints while preserving high performance. Our approach, inspired by Matryoshka Representation Learning, encodes audio-visual representations at multiple granularities within a single model, eliminating the need to train separate models for different compression levels. Moreover, to efficiently fine-tune the LLM, we introduce three LoRA-based Matryoshka strategies using global and scale-specific LoRA modules. Extensive evaluations on the two largest AVSR datasets demonstrate that Llama-MTSK achieves state-of-the-art results, matching or surpassing models trained independently at fixed compression levels.

Related papers

• MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens [40.95973318669374]
  We introduce an efficient multimodal speech LLM framework that minimizes token length while preserving essential linguistic content. Our approach achieves state-of-the-art performance with a WER of 0.74% while using only 3.5 tokens per second.
  arXiv  Detail & Related papers  (2025-03-14T11:31:30Z)
• 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)
• RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition [78.97487780589574]
  Multimodal Large Language Models (MLLMs) excel at classifying fine-grained categories. This paper introduces a Retrieving And Ranking augmented method for MLLMs. Our proposed approach not only addresses the inherent limitations in fine-grained recognition but also preserves the model's comprehensive knowledge base.
  arXiv  Detail & Related papers  (2024-03-20T17:59:55Z)
• Connecting Speech Encoder and Large Language Model for ASR [25.660343393359565]
  The impressive capability and versatility of large language models (LLMs) have aroused increasing attention in automatic speech recognition (ASR) This paper presents a comparative study of three commonly used structures as connectors, including fully connected layers, multi-head cross-attention, and Q-Former. Experiments were performed on the commonly used LibriSpeech, Common Voice, and GigaSpeech datasets.
  arXiv  Detail & Related papers  (2023-09-25T08:57:07Z)
• 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)
• AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR [79.21857972093332]
  We present AVFormer, a method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We show that these can be trained on a small amount of weakly labelled video data with minimum additional training time and parameters. We also introduce a simple curriculum scheme during training which we show is crucial to enable the model to jointly process audio and visual information effectively.
  arXiv  Detail & Related papers  (2023-03-29T07:24:28Z)
• 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)
• SLICER: Learning universal audio representations using low-resource self-supervised pre-training [53.06337011259031]
  We present a new Self-Supervised Learning approach to pre-train encoders on unlabeled audio data. Our primary aim is to learn audio representations that can generalize across a large variety of speech and non-speech tasks.
  arXiv  Detail & Related papers  (2022-11-02T23:45:33Z)
• MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition [54.84624870942339]
  MixSpeech is a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR) We apply MixSpeech on two popular end-to-end speech recognition models including LAS (Listen, Attend and Spell) and Transformer. Experimental results show that MixSpeech achieves better accuracy than the baseline models without data augmentation.
  arXiv  Detail & Related papers  (2021-02-25T03:40:43Z)
• 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)

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.