Topic
Viseme
About: Viseme is a research topic. Over the lifetime, 865 publications have been published within this topic receiving 17889 citations.
Papers published on a yearly basis
Papers
More filters
20 Oct 2007
TL;DR: An approach to large lexicon sign recognition that does not require tracking overcomes the issues of how to accurately track the hands through self occlusion in unconstrained video, instead opting to take a detection strategy, where patterns of motion are identified.
Abstract: This paper presents an approach to large lexicon sign recognition that does not require tracking. This overcomes the issues of how to accurately track the hands through self occlusion in unconstrained video, instead opting to take a detection strategy, where patterns of motion are identified. It is demonstrated that detection can be achieved with only minor loss of accuracy compared to a perfectly tracked sequence using coloured gloves. The approach uses two levels of classification. In the first, a set of viseme classifiers detects the presence of sub-Sign units of activity. The second level then assembles visemes into word level Sign using Markov chains. The system is able to cope with a large lexicon and is more expandable than traditional word level approaches. Using as few as 5 training examples the proposed system has classification rates as high as 74.3% on a randomly selected 164 sign vocabulary performing at a comparable level to other tracking based systems.
84 citations
Book•
01 Jan 1973
TL;DR: An evaluation of the state of the art and a program for research towards the development of speech understanding systems to assess the possibility of such systems four specific tasks were considered and evaluated.
Abstract: This report provides an evaluation of the state of the art and a program for research towards the development of speech understanding systems. To assess the possibility of such systems four specific tasks were considered and evaluated. Problem areas are identified and discussed leading to the conclusions on the technical aspects of the study. A possible program for research and development is presented.
84 citations
15 Apr 2007
TL;DR: In this article, a profile view (PV) lip reading scheme for speaker-dependent isolated word speech recognition was proposed, based on the importance of profile images in facial animation for lip reading.
Abstract: In this paper, we introduce profile view (PV) lip reading, a scheme for speaker-dependent isolated word speech recognition. We provide historic motivation for PV from the importance of profile images in facial animation for lip reading, and we present feature extraction schemes for PV as well as for the traditional frontal view (FV) approach. We compare lip reading results for PV and FV, which demonstrate a significant improvement for PV over FV. We show improvement in speech recognition with the integration of audio and visual features. We also found it advantageous to process the visual features over a longer duration than the duration marked by the endpoints of the speech utterance.
83 citations
TL;DR: The proposed coupled hidden Markov model (CHMM) approach to video-realistic speech animation indicates that explicitly modelling audio-visual speech is promising for speech animation.
82 citations
TL;DR: It is demonstrated that speech recognition error rates for interactive read aloud can be reduced by more than 50% through a combination of advances in both statistical language and acoustic modeling.
80 citations