We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where the uncertainty over the data is given by a Gaussian distribution. While this uncertainty is commonly exploited at the decoding stage via uncertainty decoding, it has not been exploited at the training stage so far. We introduce a new Expectation-Maximization (EM) algorithm called uncertainty training that allows to learn GMMs directly from noisy data while taking their uncertainty into account. We evaluate its potential for a speaker recognition task over speech data corrupted by real-world domestic background noise, using a state-of-the-art signal enhancement technique and various uncertainty estimation techniques as a front-end. Compared to ...
Abstract—In this paper, we study a category of robust speech recognition problem in which mismatches...
recognition problem in which mismatches exist between training and testing conditions, and no accura...
Joint uncertainty decoding (JUD) is an effective model-based noise compensation technique for conven...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
We address the problem of learning a Gaussian mixture from a set of noisy data points. Each input po...
We address the problem of learning a Gaussian mixture from a set of noisy data points. Each input po...
Abstract—In this paper, we study a category of robust speech recognition problem in which mismatches...
recognition problem in which mismatches exist between training and testing conditions, and no accura...
Joint uncertainty decoding (JUD) is an effective model-based noise compensation technique for conven...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
International audienceWe consider Gaussian mixture model (GMM)-based classification from noisy featu...
We address the problem of learning a Gaussian mixture from a set of noisy data points. Each input po...
We address the problem of learning a Gaussian mixture from a set of noisy data points. Each input po...
Abstract—In this paper, we study a category of robust speech recognition problem in which mismatches...
recognition problem in which mismatches exist between training and testing conditions, and no accura...
Joint uncertainty decoding (JUD) is an effective model-based noise compensation technique for conven...