In this paper we look at real-time computing issues in large vocabulary speech recognition. We use the French broadcast audio transcription task from ETAPE 2011 for this evaluation. We compare word error rate (WER) versus overall computing time for hidden Markov models with Gaussian mixtures (GMM-HMM) and deep neural networks (DNN-HMM). We show that for a similar computing during recognition, t...

Two approaches to detecting and tracking speakers in multispeaker audio are described. Both approaches use an adapted Gaussian mixture model, universal background model (GMM-UBM) speaker detection system as the core speaker recognition engine. In one approach, the individual log-likelihood ratio scores, which are produced on a frame-by-frame basis by the GMM-UBM system, are used to first partit...

In this paper, the statistical method of Factor Analysis(FA) is studied on Gaussian Mixture Model(GMM) based speaker identification(SI) system to model the data covariance which is usually neglected due to the training data sparseness. Because the variance of GMM can represents speaker variability, it is very important in SI systems. By FA modeled the data covariance, a relative gain of 39.6% o...

In this letter, we present a speech enhancement technique based on the ambient noise classification incorporating the Gaussian mixture model (GMM). The principal parameters of the statistical model-based speech enhancement algorithm such as the weighting parameter in the decision-directed (DD) method and the long-term smoothing parameter of the noise estimation, are chosen as different values a...

The majority of state-of-the-art speaker recognition systems (SR) utilize speaker models that are derived from an adapted universal background model (UBM) in the form of a Gaussian mixture model (GMM). This is true for GMM supervector systems, joint factor analysis systems, and most recently i-vector systems. In all of these systems, the posterior probabilities and sufficient statistics calcula...

This paper studies the reliance of a Gaussian Mixture Model (GMM) based closed-set Speaker Identification system on model convergence and describes methods to improve this convergence. It shows that the reason why the Vector Quantisation GMMs (VQGMMs) outperform a simple GMM is mainly due to decreasing the complexity of the data during training. In addition, it is shown that the VQGMM system is...

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the ...

Total Variability Model Conventionally formulated as generative model over features Assumes that feature vector distribution is a GMM Distribution Free Formulation Follows from asymptotic normality of Baum-Welch statistics Connections to probabilistic PCA, matrix completion Leads to a stochastic subgradient descent based estimation algorithm Conventional Formulation Collection of feature vector...

In this paper, we propose a method to analyze gender of the pedestrian and whether he or she has a baggage or not in a public space. The challenging part of this work is we only use top-view camera images to protect the pedestrians’ privacy. We focused on temporal changes in their position, shape, and contours over the frames because their appearances do not provide much information. We extract...

This paper presents a Bayesian approach for Gaussian mixture model (GMM)-based speaker identification. Some approaches evaluate the speaker score of a test speech utterance using a single data likelihood over the GMM learned by point estimation methods according to the maximum likelihood or maximum a posteriori criteria. In contrast, the Bayesian approach evaluates the score by using the expect...