Mel-Spectrogram Reconstruction from Video Lip Sequences Using an Autoencoder Architecture
- 24 October 2025
- book chapter
- Published by Springer Nature
- p. 55-65
Abstract
No abstract availableKeywords
This publication has 11 references indexed in Scilit:
- LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip ReadingIEEE Transactions on Neural Networks and Learning Systems, 2022
- A survey on epistemic (model) uncertainty in supervised learning: Recent advances and applicationsNeurocomputing, 2022
- Speech Emotion Recognition System With Librosa2021
- LipSound: Neural Mel-Spectrogram Reconstruction for Lip Reading2019
- LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild2019
- Lip2Audspec: Speech Reconstruction from Silent Lip Movements Video2018
- Lip Reading in the Wild2017
- Vid2speech: Speech reconstruction from silent video2017
- Reconstruction of Normal Sounding Speech for Laryngectomy Patients Through a Modified CELP CodecIEEE Transactions on Biomedical Engineering, 2010
- An audio-visual corpus for speech perception and automatic speech recognitionThe Journal of the Acoustical Society of America, 2006