Publication
Spectral Entropy Based Feature for Robust ASR
Related publications (34)
Audio-visual reliability estimates using stream entropy for speech recognition
Jean-Philippe Thiran, Mihai Gurban
We present a method for multimodal fusion based on the estimated reliability of each individual modality. Our method uses an information theoretic measure, the entropy derived from the state probability distribution for each stream, as an estimate of relia ...
2009Quantum distillation: Dynamical generation of low-entropy states of strongly correlated fermions in an optical lattice
Correlations between particles can lead to subtle and sometimes counterintuitive phenomena. We analyze one such case, occurring during the sudden expansion of fermions in a lattice when the initial state has a strong admixture of double occupancies. We pro ...
2009Using entropy as a stream reliability estimate for audio-visual speech recognition
Jean-Philippe Thiran, Mihai Gurban
We present a method for dynamically integrating audio-visual information for speech recognition, based on the estimated reliability of the audio and visual streams. Our method uses an information theoretic measure, the entropy derived from the state probab ...
2008Extraction of audio features specific to speech production for multimodal speaker detection
Jean-Philippe Thiran, Jean-Marc Vesin, Murat Kunt, Vlad Popovici, Patricia Besson
A method that exploits an information theoretic framework to extract optimized audio features using video information is presented. A simple measure of mutual information (MI) between the resulting audio and video features allows the detection of the activ ...
2008ON THE INEQUALITIES IN INFORMATION THEORY
Claude Elwood Shannon in 1948, then of the Bell Labs, published one of the ground breaking papers in the history of engineering [1]. This paper (”A Mathematical Theory of Communication”, Bell System Tech. Journal, Vol. 27, July and October 1948, pp. 379 - ...
2007A multimodal pattern recognition framework for speaker detection
Speaker detection is an important component of a speech-based user interface. Audiovisual speaker detection, speech and speaker recognition or speech synthesis for example find multiple applications in human-computer interaction, multimedia content indexin ...
EPFL2007Multi-stream Processing for Noise Robust Speech Recognition
In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...
École Polytechnique Fédérale de Lausanne2006Multi-stream Processing for Noise Robust Speech Recognition
In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...
IDIAP2006Multi-stream processing for noise robust speech recognition
In this thesis, the framework of multi-stream combination has been explored to improve the noise robustness of automatic speech recognition (ASR) systems. The central idea of multi-stream ASR is to combine information from several sources to improve the pe ...
EPFL2006Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models
Mobile service robots are going to play an increasing role in the society of humans. Voice-enabled interaction with service robots becomes very important, if such robots are to be deployed in real-world environments and accepted by the vast majority of pot ...
EPFL2006