Lipger: Visually-conditioned Generative Error Correction For Robust Automatic Speech Recognition

Abstract

Visual cues, like lip motion, have been shown to improve the performance of Automatic Speech Recognition (ASR) systems in noisy environments. We propose LipGER (Lip Motion aided Generative Error Correction), a novel framework for leveraging visual cues for noise-robust ASR. Instead of learning the cross-modal correlation between the audio and visual modalities, we make an LLM learn the task of visually-conditioned (generative) ASR error correction. Specifically, we instruct an LLM to predict the transcription from the N-best hypotheses generated using ASR beam-search. This is further conditioned on lip motions. This approach addresses key challenges in traditional AVSR learning, such as the lack of large-scale paired datasets and difficulties in adapting to new domains. We experiment on 4 datasets in various settings and 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 that is add

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyghosh2024lipger

Related papers

• Listening And Seeing Again: Generative Error Correction For Audio-visual Speech Recognition (2025)1.20
• Lipvoicer: Generating Speech From Silent Videos Guided By Lip Reading (2023)3.89
• Lip2vec: Efficient And Robust Visual Speech Recognition Via Latent-to-latent Visual To Audio Representation Mapping (2023)6.77
• Whispering Llama: A Cross-modal Generative Error Correction Framework For Speech Recognition (2023)16.15
• Large Language Model Based Generative Error Correction: A Challenge And Baselines For Speech Recognition, Speaker Tagging, And Emotion Recognition (2024)7.81
• Lipper: Synthesizing Thy Speech Using Multi-view Lipreading (2019)10.61
• Lipsound2: Self-supervised Pre-training For Lip-to-speech Reconstruction And Lip Reading (2021)11.39
• GEC-RAG: Improving Generative Error Correction Via Retrieval-augmented Generation For Automatic Speech Recognition Systems (2025)0.00