u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality
Computation and Language2022-11-29v2Artificial IntelligenceComputer Vision and Pattern RecognitionSoundAudio and Speech ProcessingImage and Video Processing
While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one model per modality. In this paper, we present u-HuBERT, a self-supervised pre-training framework that can leverage both multimodal and unimodal speech with a unified masked cluster prediction objective. By utilizing modality dropout during pre-training, we demonstrate that a single fine-tuned model can achieve performance on par or better than the state-of-the-art modality-specific models. Moreover, our model fine-tuned only on audio can perform well with audio-visual and visual speech input, achieving zero-shot modality generalization for multiple speech processing tasks. In particular, our single model yields 1.2%/1.4%/27.2% speech recognition word error rate on LRS3 with audio-visual/audio/visual input. Codes and models are available at https://github.com/facebookresearch/av_hubert
@article{arxiv.2207.07036,
title = {u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality},
author = {Wei-Ning Hsu and Bowen Shi},
journal= {arXiv preprint arXiv:2207.07036},
year = {2022}
}