Active Shape Models for Visual Speech Feature Extraction

Luettin, Juergen; Thacker, Neil A.; Beet, S.W.

doi:10.1007/978-3-662-13015-5_28

Cited by 62 publications

(35 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are obtained from the tracking results and serve as features for the recognition system. We have described the detailed feature extraction method elsewhere [16 ] [17 ].…”

Section: Feature Extractionmentioning

confidence: 99%

Learning to recognise talking faces

Luettin

Thacker

Beet³

1996

Proceedings of 13th International Conference on Pattern Recognition

View full text Add to dashboard Cite

An approach for person identification is described based on spatio-temporal analysis of the talking face. A person is represented by a parametric model of the visible speech articulators and their temporal characteristics during speech production. The model consists of shape parameters, representing the lip contour and intensity parameters representing the grey level distribution in the mouth region. The model is used to track lips in image sequences where the model parameters are recovered from the tracking results. While some of these parameters relate to speech information, others are intuitively related to different persons and we show that models based on these features enable successful person identification. We model the shape and intensity parameters as mixtures of Gaussians and their temporal dependencies by Hidden Markov Models. Identifying a talking person is performed by estimating the likelihood of each model for having generated the observed sequence of features and the model with the highest likelihood is chosen as the identified person.

show abstract

“…They are obtained from the tracking results and serve as features for the recognition system. We have described the detailed feature extraction method elsewhere [16 ] [17 ].…”

Section: Feature Extractionmentioning

confidence: 99%

Learning to recognise talking faces

Luettin

Thacker

Beet³

1996

Proceedings of 13th International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Despite years of research attention, there has been limited success in creating a system that can reliably detect lips in unconstrained imagery. Existing systems employ methods such as snake and active shape models [5,6], Markov Random Field (MRF) techniques [7], and multi-class, shape-guided fuzzy c-means (FCM) clustering algorithm [8], to detect and locate lips within an image. While the results are commendable, the extensive calculations demanded by these methods are significant.…”

Section: Introductionmentioning

confidence: 99%

Building a Visual Front-end for Audio-Visual Automatic Speech Recognition in Vehicle Environments

Hursig¹,

Zhang²

2011

Speech and Language Technologies

View full text Add to dashboard Cite

“…One of the early visual speech recognition systems was developed by Petajan [19] in which the shape of the lips was sampled by simple morphological features including height, width and area of the lips contour. Later in 1995, Luettin et al [6] applied Active Shape Models (ASM) in order to extract the lips outline and this information was used in the recognition of a set of standard English phonemes. A different approach was proposed by Harvey et al [17] where they applied a morphological transform called sieve that was applied to calculate simple one-dimensional (1D) and two-dimensional (2D) measurements that were employed to sample the lips shapes.…”

Section: Introductionmentioning

confidence: 99%

A PCA based manifold representation for visual speech recognition

Yu¹,

Ghita²,

Sutherland³

et al. 2007

China-Ireland International Conference on Information and Communications Technologies (CIICT 2007)

View full text Add to dashboard Cite

In this paper, we discuss a new Principal Component Analysis (PCA)-based manifold representation for visual speech recognition. In this regard, the real time input video data is compressed using Principal Component Analysis and the low-dimensional points calculated for each frame define the manifold. Since the number of frames that form the video sequence is dependent on the word complexity, in order to use these manifolds for visual speech classification it is required to re-sample them into a fixed pre-defined number of key-points. These key-points are used as input for a Hidden Markov Model (HMM) classification scheme. We have applied the developed visual speech recognition system to a database containing a group of English words and the experimental data indicates that the proposed approach is able to produce accurate classification results.

show abstract

Active Shape Models for Visual Speech Feature Extraction

Cited by 62 publications

References 4 publications

Learning to recognise talking faces

Learning to recognise talking faces

Building a Visual Front-end for Audio-Visual Automatic Speech Recognition in Vehicle Environments

A PCA based manifold representation for visual speech recognition

Contact Info

Product

Resources

About