• Publications
  • Influence
The interpolated fast Fourier transform: a comparative study
The properties of five interpolating fast Fourier transform methods (IFFT) are studied with respect to their systematic errors and their noise sensitivity, for a monofrequency signal. It is shownExpand
Parametric identification of transfer functions in the frequency domain-a survey
This paper gives a survey of frequency domain identification methods for rational transfer functions in the Laplace (s) or z-domain. The interrelations between the different approaches areExpand
HAC-models: a novel approach to continuous speech recognition
A bottom-up, activation-based paradigm for continuous speech recognition is described, using a vectorial representation of high but fixed dimension called “Histogram of Acoustic Co-occurrence” (HAC). Expand
An exemplar-based NMF approach to audio event detection
A novel, exemplar-based method for audio event detection based on non-negative matrix factorisation, which model events as a linear combination of dictionary atoms, and mixtures as alinear combination of overlapping events. Expand
Age Estimation from Telephone Speech using i-vectors
A new approach for age estimation from telephone speech patterns based on i-vectors, where each utterance is modeled by its corresponding ivector and Support Vector Regression is applied to estimate the age of speakers. Expand
PROSPECT features and their application to missing data techniques for robust speech recognition
Alternative to the cepstral representation that lead to more efficient MDT systems are studied, and the proposed solution, PROSPECT features (Projected Spectra), can be interpreted as a novel speech representation, or as an approximation of the inverse covariance matrix of the Gaussian distributions modeling the log-spectra. Expand
A Review of Signal Subspace Speech Enhancement and Its Application to Noise Robust Speech Recognition
An extensive overview of the available estimators is presented, and a theoretical estimator is derived to experimentally assess an upper bound to the performance that can be achieved by any subspace-based method. Expand
Speaker age estimation using i-vectors
In this method, each utterance is modeled by its corresponding i-vector, and a Within-Class Covariance Normalization technique is used for session variability compensation and a least squares support vector regression is applied to estimate the age of speakers. Expand
Self-taught assistive vocal interfaces: an overview of the ALADIN project
The overall learning framework, the user-centred design and evaluation aspects, database collection and approaches taken to combat problems such as noise and erroneous input are described. Expand
Model-based feature enhancement with uncertainty decoding for noise robust ASR
This paper illustrates that the Gaussian observation pdf can be replaced by a computationally more tractable discrete pdf, consisting of a weighted sum of delta functions, and shows how improved posterior state probabilities can be obtained by calculating their maximum likelihood estimates or using the pdf of clean speech conditioned on both the noisy speech and the backend Gaussian. Expand