Sylvio Barbon Junior

A neural-wavelet architecture for voice conversion

In this letter we propose a new architecture for voice conversion that is based on a joint neural-wavelet approach. We also examine the characteristics of many wavelet families and determine the one that best matches the requirements of the proposed system. The conclusions presented in theory are confirmed in practice with utterances extracted from TIMIT speech corpus.

Autoregressive decomposition and pole tracking applied to vocal fold nodule signals

This letter describes a novel algorithm that is based on autoregressive decomposition and pole tracking used to recognize two patterns of speech data: normal voice and disphonic voice caused by nodules. The presented method relates the poles and the peaks of the signal spectrum which represent the periodic components of the voice. The results show that the perturbation contained in the signal is clearly depicted by poles positions. Their variability is related to jitter and shimmer. The pole dispersion for pathological voices is about 20% higher than for normal voices, therefore, the proposed approach is a more trustworthy measure than the classical ones.

SPOKEN DOCUMENT SUMMARIZATION BASED ON DYNAMIC TIME WARPING AND WAVELETS

This work presents a spoken document summarization (SDS) scheme that is based on an improved version of the Dynamic Time Warping (DTW) algorithm, and on the Discrete Wavelet Transform (DWT). Tests and results with sentences extracted from TIMIT speech corpus show the efficacy of the proposed technique.

Strict Very Fast Decision Tree: A memory conservative algorithm for data stream mining

Dealing with memory and time constraints are current challenges when learning from data streams with a massive amount of data. Many algorithms have been proposed to handle these difficulties, among them, the Very Fast Decision Tree (VFDT) algorithm. Although the VFDT has been widely used in data stream mining, in the last years, several authors have suggested modifications to increase its performance, putting aside memory concerns by proposing memory-costly solutions. Besides, most data stream mining solutions have been centred around ensembles, which combine the memory costs of their weak learners, usually VFDTs. To reduce the memory cost, keeping the predictive performance, this study proposes the Strict VFDT (SVFDT), a novel algorithm based on the VFDT. The SVFDT algorithm minimises unnecessary tree growth, substantially reducing memory usage and keeping competitive predictive performance. Moreover, since it creates much more shallow trees than VFDT, SVFDT can achieve a shorter processing time. Experiments were carried out comparing the SVFDT with the VFDT in 11 benchmark data stream datasets. This comparison assessed the trade-off between accuracy, memory, and processing time. Statistical analysis showed that the proposed algorithm obtained similar predictive performance and significantly reduced processing time and memory use. Thus, SVFDT is a suitable option for data stream mining with memory and time limitations, recommended as a weak learner in ensemble-based solutions.

Applying multi-label techniques in emotion identification of short texts

Abstract Sentiment Analysis is an emerging research field traditionally applied to classify opinions, sentiments and emotions towards polarity and subjectivity expressed in text. An important characteristic to automatic emotion analysis is the standpoint, in which we can look at an opinion from two perspectives, the opinion holder (author) who express an opinion, and the reader who reads and perceives the opinion. From the reader’s standpoint, the interpretations of the text can be multiple and depend on the personal background. The multiple standpoints cognition, in which readers can look at the same sentence, is an interesting scenario to use the multi-label classification paradigm in the Sentiment Analysis domain. This methodology is able to handle different target sentiments simultaneously in the same text, by also taking advantage of the relations between them. We applied different approaches such as algorithm adaptation, problem transformation and ensemble methods in order to explore the wide range of multi-label solutions. The experiments were conducted on 10,080 news sentences from two different real datasets. Experimental results showed that the Ensemble Classifier Chain overcame the other algorithms, average F-measure of 64.89% using emotion strength features, when considering six emotions and neutral sentiment.

A Framework for Human-in-the-loop Monitoring of Concept-drift Detection in Event Log Stream

One of the main challenges of Cognitive Computing (CC) is reacting to evolving environments in near-real time. Therefore, it is expected that CC models provide solutions by examining a summary of past history, rather than using full historical data. This strategy has significant benefits in terms of response time and space complexity but poses new challenges in term of concept-drift detection, where both long term and short terms dynamics should be taken into account. In this paper, we introduce the Concept-Drift in Event Stream Framework (CDESF) that addresses some of these challenges for data streams recording the execution of a Web-based business process. Thanks to CDESF support for feature transformation, we perform density clustering in the transformed feature space of the process event stream, observe track concept-drift over time and identify anomalous cases in the form of outliers. We validate our approach using logs of an e-healthcare process.

On the Determination of Epsilon during Discriminative GMM Training

Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, epsilon, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine epsilon, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm.

A Fractal and Wavelet-Based Approach for Audio Coding.

Towards an optimization-oriented approach for audio coding, this paper presents improved rate-distortion and perceptual strategies for bit allocation. The algorithm is based on best basis wavelet-packet trees and fractal dimension calculation. Transparent coding of high quality audio, signals sampled at 44.1 KHz using 16 bits PCM, is effectively achieved at low bit rates. Real time working of the decoder is confirmed, reassuring the usability of the proposed technique