CLASSPApr 9, 2025

Visual-Aware Speech Recognition for Noisy Scenarios

arXiv:2504.07229v12 citationsh-index: 1EMNLP
Originality Incremental advance
AI Analysis

This work addresses speech recognition challenges in noisy scenarios for applications like communication systems, though it is incremental by building on existing audio-visual methods.

The paper tackles the problem of automatic speech recognition in noisy environments by proposing a model that uses visual cues from the environment to filter noise, resulting in significant improvements over audio-only models.

Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech Recognition (AVSR) models often struggle in noisy scenarios. To solve this task, we propose a model that improves transcription by correlating noise sources to visual cues. Unlike works that rely on lip motion and require the speaker's visibility, we exploit broader visual information from the environment. This allows our model to naturally filter speech from noise and improve transcription, much like humans do in noisy scenarios. Our method re-purposes pretrained speech and visual encoders, linking them with multi-headed attention. This approach enables the transcription of speech and the prediction of noise labels in video inputs. We introduce a scalable pipeline to develop audio-visual datasets, where visual cues correlate to noise in the audio. We show significant improvements over existing audio-only models in noisy scenarios. Results also highlight that visual cues play a vital role in improved transcription accuracy.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes