Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation

• URL: http://arxiv.org/abs/2504.18539v2
• Date: Wed, 30 Apr 2025 05:16:51 GMT
• Title: Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
• Authors: Sungnyun Kim, Sungwoo Cho, Sangmin Bae, Kangwook Jang, Se-Young Yun,
• Abstract summary: We propose CAV2vec, a novel self-supervised speech representation learning framework to handle audio-visual joint corruption.<n>We suggest a unimodal multi-task learning, which distills cross-modal knowledge and aligns the corrupted modalities.<n>Our experiments on robust AVSR benchmarks demonstrate that the corrupted representation learning method significantly enhances recognition accuracy.
• Score: 23.406334722946163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech systems are insufficient. While previous research has largely addressed audio disruptions, few studies have dealt with visual corruptions, e.g., lip occlusions or blurred videos, which are also detrimental. To address this real-world challenge, we propose CAV2vec, a novel self-supervised speech representation learning framework particularly designed to handle audio-visual joint corruption. CAV2vec employs a self-distillation approach with a corrupted prediction task, where the student model learns to predict clean targets, generated by the teacher model, with corrupted input frames. Specifically, we suggest a unimodal multi-task learning, which distills cross-modal knowledge and aligns the corrupted modalities, by predicting clean audio targets with corrupted videos, and clean video targets with corrupted audios. This strategy mitigates the dispersion in the representation space caused by corrupted modalities, leading to more reliable and robust audio-visual fusion. Our experiments on robust AVSR benchmarks demonstrate that the corrupted representation learning method significantly enhances recognition accuracy across generalized environments involving various types of corruption. Our code is available at https://github.com/sungnyun/cav2vec.

Related papers

• Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization [59.1277150358203]
  We propose using a preference optimization strategy to improve speech recognition accuracy for real-world videos.<n>First, we create preference data via simulating common errors that occurred in AV-ASR from two focals.<n>Second, we propose BPO-AVASR, a Bifocal Preference Optimization method to improve AV-ASR models by leveraging both input-side and output-side preference.
  arXiv  Detail & Related papers  (2024-12-26T00:26:45Z)
• AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection [2.985620880452743]
  We present Audio-Visual Feature Fusion (AVFF), a two-stage cross-modal learning method for improved deepfake detection. To extract rich cross-modal representations, we use contrastive learning and autoencoding objectives, and introduce a novel audio-visual masking and feature fusion strategy. We report 98.6% accuracy and 99.1% AUC on the FakeAVCeleb dataset, outperforming the current audio-visual state-of-the-art by 14.9% and 9.9%, respectively.
  arXiv  Detail & Related papers  (2024-06-05T05:20:12Z)
• AdVerb: Visually Guided Audio Dereverberation [49.958724234969445]
  We present AdVerb, a novel audio-visual dereverberation framework. It uses visual cues in addition to the reverberant sound to estimate clean audio.
  arXiv  Detail & Related papers  (2023-08-23T18:20:59Z)
• Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping [4.271091833712731]
  We propose a simple approach, named Lip2Vec that is based on learning a prior model. The proposed model compares favorably with fully-supervised learning methods on the LRS3 dataset achieving 26 WER. We believe that reprogramming the VSR as an ASR task narrows the performance gap between the two and paves the way for more flexible formulations of lip reading.
  arXiv  Detail & Related papers  (2023-08-11T12:59:02Z)
• Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation [18.001730255429347]
  Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. We propose a new cost-effective strategy to build challenging and relatively unbiased high-quality audio-visual segmentation benchmarks. Experiments conducted on existing AVS datasets and on our new benchmark show that our method achieves state-of-the-art (SOTA) segmentation accuracy.
  arXiv  Detail & Related papers  (2023-04-06T09:54:06Z)
• Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring [29.05833230733178]
  This paper deals with Audio-Visual Speech Recognition (AVSR) under multimodal input corruption situations. In real life, clean visual inputs are not always accessible and can even be corrupted by occluded lip regions or noises. We propose a novel AVSR framework, namely Audio-Visual ReliabilityScore module (AV-RelScore), that is robust to the corrupted multimodal inputs.
  arXiv  Detail & Related papers  (2023-03-15T11:29:36Z)
• Jointly Learning Visual and Auditory Speech Representations from Raw Data [108.68531445641769]
  RAVEn is a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our design is asymmetric w.r.t. driven by the inherent differences between video and audio. RAVEn surpasses all self-supervised methods on visual speech recognition.
  arXiv  Detail & Related papers  (2022-12-12T21:04:06Z)
• Multimodal Attention Fusion for Target Speaker Extraction [108.73502348754842]
  We propose a novel attention mechanism for multi-modal fusion and its training methods. Our proposals improve signal to distortion ratio (SDR) by 1.0 dB over conventional fusion mechanisms on simulated data.
  arXiv  Detail & Related papers  (2021-02-02T05:59:35Z)
• Self-Supervised Learning of Audio-Visual Objects from Video [108.77341357556668]
  We introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate information over time. We demonstrate the effectiveness of the audio-visual object embeddings that our model learns by using them for four downstream speech-oriented tasks.
  arXiv  Detail & Related papers  (2020-08-10T16:18:01Z)
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision [63.564385139097624]
  We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio) Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.
  arXiv  Detail & Related papers  (2020-07-08T14:07:06Z)
• How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition [10.74796391075403]
  This study investigates the inner workings of AV Align and visualises the audio-visual alignment patterns. We find that AV Align learns to align acoustic and visual representations of speech at the frame level on TCD-TIMIT in a generally monotonic pattern. We propose a regularisation method which involves predicting lip-related Action Units from visual representations.
  arXiv  Detail & Related papers  (2020-04-17T13:59:19Z)

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.