Relevant Feature Selection for Audio-Visual Speech Recognition
Related publications (51)
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
Feature selection problems arise in a variety of applications, such as microarray analysis, clinical prediction, text categorization, image classification and face recognition, multi-label learning, and classification of internet traffic. Among the various ...
Object classification and detection aim at recognizing and localizing objects in real-world images. They are fundamental computer vision problems and a prerequisite for full scene understanding. Their difficulty lies in the large number of possible object ...
Programme doctoral en Informatique, Communications et Information2013
The continuous increase, witnessed in the last decade, of both the amount of available data and the areas of application of machine learning, has lead to a demand for both learning and planning algorithms that are capable of handling large-scale problems. ...
Standard automatic speech recognition (ASR) systems use phonemes as subword units. Thus, one of the primary resource required to build a good ASR system is a well developed phoneme pronunciation lexicon. However, under-resourced languages typically lack su ...
In this work, we present a simple biometric indexing scheme which is binning and retrieving cancelable deep face templates based on frequent binary patterns. The simplicity of the proposed approach makes it applicable to unprotected as well as protected, i ...
HMMs have been the one of the first models to be applied for sign recognition and have become the baseline models due to their success in modeling sequential and multivariate data. Despite the extensive use of HMMs for sign recognition, determining the HMM ...
In this report we study the ways to exploit the vast amount of information inherent in the plenoptic space and constraints of the plenoptic function to improve the efficiency of image retrieval, recognition and matching techniques. The specific application ...
Although the Internet of Things allows seamless access to billions of sensors readily deployed throughout the world, current context- and activity-recognition approaches restrict ambient intelligence to domains where dedicated sensors are deployed. The big ...
Institute of Electrical and Electronics Engineers2013
Standard automatic speech recognition (ASR) systems use phonemes as subword units. Thus, one of the primary resource required to build a good ASR system is a well developed phoneme pronunciation lexicon. However, under-resourced languages typically lack su ...
This paper proposes a new method for recognizing both activities and gestures by using acceleration data collected on a smartwatch. While both activity recognition techniques and gesture recognition techniques employ acceleration data, these techniques are ...