Publication
Spectral Entropy Based Feature for Robust ASR
Publications associées (34)
Multi-resolution Spectral Entropy Based Feature for Robust ASR
Hervé Bourlard, Hemant Misra, Shajith Ikbal
Recently, entropy measures at different stages of recognition have been used in automatic speech recognition (ASR) task. In a recent paper, we proposed that formant positions of a spectrum can be captured by multi-resolution spectral entropy feature. In th ...
2005Spectral Entropy Feature in Multi-stream for Robust ASR
In recent papers, entropy computed from sub-bands of the spectrum was used as a feature for automatic speech recognition. In the present paper, we further study the sub-band spectral entropy features which can give the flatness/peakiness of the sub-band sp ...
IDIAP2005Stochasticity of probabilistic systems: Analysis methodologies case-study
Karl Aberer, Martin Hasler, Abhisek Datta
We do a case study of two different analysis techniques for studying the stochastic behavior of a randomized system/algorithms: (i) The first approach can be broadly termed as a mean value analysis (MVA), where the evolution of the mean state is studied as ...
2005Impact of Sample Sizes on Information Theoretic Measures for Audio-Visual Signal Processing
Jean-Philippe Thiran, Ninoslav Marina, Ivana Arsic de Heras Ciechomska
In this paper we aim to explore what is the most appropriate number of data samples needed when measuring the temporal correspondence between a chosen set of video and audio cues in a given audio-visual sequence. Presently the optimal model that connects s ...
IEEE2005Multi-resolution Spectral Entropy Based Feature for Robust ASR
Hervé Bourlard, Hemant Misra, Shajith Ikbal
Recently, entropy measures at different stages of recognition have been used in automatic speech recognition (ASR) task. In a recent paper, we proposed that formant positions of a spectrum can be captured by multi-resolution spectral entropy feature. In th ...
IDIAP2004Nonlinear feature transformations for noise robust speech recognition
Robustness against external noise is an important requirement for automatic speech recognition (ASR) systems, when it comes to deploying them for practical applications. This thesis proposes and evaluates new feature-based approaches for improving the ASR ...
EPFL2004Spectral Entropy Based Feature for Robust ASR
Hervé Bourlard, Hynek Hermansky, Hemant Misra, Shajith Ikbal
In general, entropy gives us a measure of the number of bits required to represent some information. When applied to probability mass function (PMF), entropy can also be used to measure the ``peakiness'' of a distribution. In this paper, we propose using t ...
IDIAP2003Speech/Music Discrimination using Entropy and Dynamism Features in a HMM Classification Framework
Hervé Bourlard, Jitendra Ajmera
In this paper, we present a new approach towards high performance speech/music discrimination on realistic tasks related to the automatic transcription of broadcast news. In the approach presented here, the (local) Probability Density Function (PDF) estima ...
2003On Multi-scale Fourier Transform Analysis of Speech Signals
In this paper, we introduce a novel algorithm to perform multi-scale Fourier transform analysis of piecewise stationary signals with application to automatic speech recognition. Such signals are composed of quasi-stationary segments of variable lengths. Th ...
IDIAP2003HMM Mixtures (HMM2) for Robust Speech Recognition
State-of-the-art automatic speech recognition (ASR) techniques are typically based on hidden Markov models (HMMs) for the modeling of temporal sequences of feature vectors extracted from the speech signal. At the level of each HMM state, Gaussian mixture m ...
Ecole Polytechnique Federale de Lausanne2003