Lipreading With Long Short-term Memory

Abstract

Lipreading, i.e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods. Feed-forward and recurrent neural network layers (namely Long Short-Term Memory; LSTM) are stacked to form a single structure which is trained by back-propagating error gradients through all the layers. The performance of such a stacked network was experimentally evaluated and compared to a standard Support Vector Machine classifier using conventional computer vision features (Eigenlips and Histograms of Oriented Gradients). The evaluation was performed on data from 19 speakers of the publicly available GRID corpus. With 51 different words to classify, we report a best word accuracy on held-out evaluation speakers of 79.6% using the end-to-end neural network-based solution (11.6% improvement over the best feature-based solution evaluated).

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywand2016lipreading

Related papers

• Can Dnns Learn To Lipread Full Sentences? (2018)6.77
• Lipreading With 3D-2D-CNN BLSTM-HMM And Word-ctc Models (2019)0.00
• Improving Speaker-independent Lipreading With Domain-adversarial Training (2017)10.85
• Lipreading Using Temporal Convolutional Networks (2020)17.61
• Multi-grained Spatio-temporal Modeling For Lip-reading (2019)0.00
• Large-scale Visual Speech Recognition (2018)14.43
• Lipformer: Learning To Lipread Unseen Speakers Based On Visual-landmark Transformers (2023)11.49
• Learning Separable Hidden Unit Contributions For Speaker-adaptive Lip-reading (2023)0.00