Lip Reading Using Convolutional Auto Encoders as Feature Extractor

TL;DR

This paper introduces a novel lip-reading model using convolutional autoencoders for feature extraction combined with LSTM, achieving superior accuracy on standard datasets and breaking existing benchmarks.

Contribution

The paper presents a new word-level lip-reading model that employs convolutional autoencoders for feature extraction, outperforming existing models on benchmark datasets.

Findings

Achieved 98% accuracy on MIRACL-VC1, surpassing 93.4% benchmark.

Performed better than baseline CNN and LSTM models on BBC's LRW dataset.

Demonstrated the effectiveness of autoencoder features in lip-reading tasks.

Abstract

Visual recognition of speech using the lip movement is called Lip-reading. Recent developments in this nascent field uses different neural networks as feature extractors which serve as input to a model which can map the temporal relationship and classify. Though end to end sentence level Lip-reading is the current trend, we proposed a new model which employs word level classification and breaks the set benchmarks for standard datasets. In our model we use convolutional autoencoders as feature extractors which are then fed to a Long short-term memory model. We tested our proposed model on BBC's LRW dataset, MIRACL-VC1 and GRID dataset. Achieving a classification accuracy of 98% on MIRACL-VC1 as compared to 93.4% of the set benchmark (Rekik et al., 2014). On BBC's LRW the proposed model performed better than the baseline model of convolutional neural networks and Long short-term memory model (Garg et al., 2016). Showing the features learned by the models we clearly indicate how the proposed model works better than the baseline model. The same model can also be extended for end to end sentence level classification.