LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading

The aim of this work is to investigate the impact of crossmodal self-supervised pre-training for speech reconstruction (video-to-audio) by leveraging the natural co-occurrence of audio and visual streams in videos. We propose LipSound2 which consists of an encoder-decoder architecture and location-aware attention mechanism to map face image sequences to mel-scale spectrograms directly without requiring any human annotations. The proposed LipSound2 model is firstly pre-trained on ~2400h multi-lingual (e.g. English and German) audio-visual data (VoxCeleb2). To verify the generalizability of the proposed method, we then fine-tune the pre-trained model on domain-specific datasets (GRID, TCD-TIMIT) for English speech reconstruction and achieve a significant improvement on speech quality and intelligibility compared to previous approaches in speaker-dependent and -independent settings. In addition to English, we conduct Chinese speech reconstruction on the CMLR dataset to verify the impact on transferability. Lastly, we train the cascaded lip reading (video-to-text) system by fine-tuning the generated audios on a pre-trained speech recognition system and achieve state-of-the-art performance on both English and Chinese benchmark datasets.

@InProceedings{QWW21, 
 	 author =  {Qu, Leyuan and Weber, Cornelius and Wermter, Stefan},  
 	 title = {LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading}, 
 	 booktitle = {arXiv:2112.04748},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {},
 	 year = {2021},
 	 month = {Dec},
 	 publisher = {},
 	 doi = {}, 
 }