LRS-3

LRS-3 is a dataset used to evaluate audio-visual speech recognition (AVSR) systems, containing diverse spoken conversations with human-annotated transcriptions.

Papers using LRS-3 (31)

DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility2025 · 4 citesMMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens2025 · 3 citesLarge Language Models are Strong Audio-Visual Speech Recognition Learners2024 · 1 citesVisG AV-HuBERT: Viseme-Guided AV-HuBERT2026LRS-VoxMM: A benchmark for in-the-wild audio-visual speech recognition2026Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition2026Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder2026MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition2025Training Strategies for Modality Dropout Resilient Multi-Modal Target Speaker Extraction2025Online Audio-Visual Autoregressive Speaker Extraction2025LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models2025Reading to Listen at the Cocktail Party: Multi-Modal Speech Separation2025Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction2022 · 113 citesLip-to-Speech Synthesis in the Wild with Multi-task Learning2023 · 20 citesu-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality2022 · 16 citesJointly Learning Visual and Auditory Speech Representations from Raw Data2022 · 13 citesReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement2022 · 4 citesRobust Self-Supervised Audio-Visual Speech Recognition2022 · 3 citesImaginary Voice: Face-styled Diffusion Model for Text-to-Speech2023 · 2 citesCross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition2023 · 2 citesSVTS: Scalable Video-to-Speech Synthesis2022 · 1 citesAV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations2023 · 1 citesLipVoicer: Generating Speech from Silent Videos Guided by Lip Reading2023 · 1 citesSeeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model2023 · 1 citesVisual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition2022Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels2023Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model2023AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition2023LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data2023Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer2024Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation2024