Related papers: Segment Boundary Detection via Class Entropy Measu…

We study the continuity property of the generalized entropy as a function of the underlying probability distribution, defined with an action space and a loss function, and use this property to answer the basic questions in statistical…

Phonemic segmentation of speech is a critical step of speech recognition systems. We propose a novel unsupervised algorithm based on sequence prediction models such as Markov chains and recurrent neural network. Our approach consists in…

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced…

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

Maximum entropy models are considered by many to be one of the most promising avenues of language modeling research. Unfortunately, long training times make maximum entropy research difficult. We present a novel speedup technique: we change…

Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent…

Prosodic boundaries in speech are of great relevance to both speech synthesis and audio annotation. In this paper, we apply the wav2vec 2.0 framework to the task of detecting these boundaries in speech signal, using only acoustic…

The quantum relative entropy is frequently used as a distance, or distinguishability measure between two quantum states. In this paper we study the relation between this measure and a number of other measures used for that purpose,…

Information-theoretic quantities, such as conditional entropy and mutual information, are critical data summaries for quantifying uncertainty. Current widely used approaches for computing such quantities rely on nearest neighbor methods and…

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned…

We propose the Linearly Adaptive Cross Entropy Loss function. This is a novel measure derived from the information theory. In comparison to the standard cross entropy loss function, the proposed one has an additional term that depends on…

Deep convolutional neural networks have been widely used in scene classification of remotely sensed images. In this work, we propose a robust learning method for the task that is secure against partially incorrect categorization of images.…

An experiment to study the entropy method for an anomaly detection system has been performed. The study has been conducted using real data generated from the distributed sensor networks at the Intel Berkeley Research Laboratory. The…

In this paper a new method of detection of homogeneous zones and singularity parts of a 1D signal is proposed. The entropy function is used to transform signal in piecewise linear one. The multiple regression permits to detect lines and…

The task of temporally grounding language queries in videos is to temporally localize the best matched video segment corresponding to a given language (sentence). It requires certain models to simultaneously perform visual and linguistic…

Connected decision boundaries are useful in several tasks like image segmentation, clustering, alpha-shape or defining a region in nD-space. However, the machine learning literature lacks methods for generating connected decision boundaries…

Entanglement entropy, which is a measure of quantum correlations between separate parts of a many-body system, has emerged recently as a fundamental quantity in broad areas of theoretical physics, from cosmology and field theory to…

This paper introduces an unsupervised method to estimate the class separability of text datasets from a topological point of view. Using persistent homology, we demonstrate how tracking the evolution of embedding manifolds during training…

In a recent paper, the authors proposed a general methodology for probabilistic learning on manifolds. The method was used to generate numerical samples that are statistically consistent with an existing dataset construed as a realization…

Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored…