Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR

About

Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We show that these can be trained on a small amount of weakly labelled video data with minimum additional training time and parameters. (ii) 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; and finally (iii) we show that our model achieves state of the art zero-shot results on three different AV-ASR benchmarks (How2, VisSpeech and Ego4D), while also crucially preserving decent performance on traditional audio-only speech recognition benchmarks (LibriSpeech). Qualitative results show that our model effectively leverages visual information for robust speech recognition.

Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid• 2023

Related benchmarks

TaskDatasetResultRank
Automatic Speech RecognitionLibriSpeech clean (test)
WER4.36
833
Audio-Visual Automatic Speech RecognitionHow2 zero-shot
WER13.69
6
Audio-Visual Automatic Speech RecognitionVisSpeech zero-shot
WER16.6
6
Audio-Visual Automatic Speech RecognitionEgo4D zero-shot
WER64.75
6
Audio-Visual Automatic Speech RecognitionHow2
WER10.22
5
Audio-Visual Automatic Speech RecognitionEgo4D
WER55.23
2
Showing 6 of 6 rows

Other info

Follow for update