Decoding visemes: improving machine lipreading

10/03/2017
by   Helen L Bear, et al.
0

To undertake machine lip-reading, we try to recognise speech from a visual signal. Current work often uses viseme classification supported by language models with varying degrees of success. A few recent works suggest phoneme classification, in the right circumstances, can outperform viseme classification. In this work we present a novel two-pass method of training phoneme classifiers which uses previously trained visemes in the first pass. With our new training algorithm, we show classification performance which significantly improves on previous lip-reading results.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/16/2023

Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension

Although the curse of multilinguality significantly restricts the langua...
research
07/01/2019

LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring

LSTM based language models are an important part of modern LVCSR systems...
research
06/09/2020

On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech

Advanced neural network models have penetrated Automatic Speech Recognit...
research
10/21/2020

LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognition

LSTM language models (LSTM-LMs) have been proven to be powerful and yiel...
research
03/16/2021

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

We introduce asynchronous dynamic decoder, which adopts an efficient A* ...
research
11/05/2019

Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation

Generally, Neural Machine Translation models generate target words in a ...
research
07/22/2022

Multilabel Prototype Generation for Data Reduction in k-Nearest Neighbour classification

Prototype Generation (PG) methods are typically considered for improving...

Please sign up or login with your details

Forgot password? Click here to reset