In this paper, we compare three approaches for decision fusion in a phoneme classification problem. We especially deal with decision-level fusion from Naive Bayes and Learning Vector Quantization (LVQ) classifiers that were trained and tested by three speech analysis techniques: Mel-frequency Cepstral Coefficients (MFCC), Relative Spectral Transform - Perceptual Linear Prediction (Rasta-PLP) and Perceptual Linear Prediction (PLP). Optimal decision making is performed with the non-parametric and parametric methods. We investigated the performance of both decision methods with a third proposed approach using fuzzy logic. The work discusses the classification of an African language phoneme namely Fongbe language and all experiments were performed on its dataset. After classification and the decision fusion, the overall decision fusion performance is obtained on test data with the proposed approach using fuzzy logic whose classification accuracies are 95,54% for consonants and 83,97% for vowels despite the lower execution time of Deep Belief Networks.
1 October 2019 in Journal of Physics: Conference Series
Ensuring the reliability of the software has become increasingly complex and challenging. The most important problem is providing failure-free software operation to prevent financial losses or machinery breakdown. It can be solved with N-version programming which requires increased costs due to the use of redundant software components. In this paradigm, redundancy refers to diversity of software components. This paper discusses the implementation of software components in various languages with different syntax. We propose an efficient and time-reducing approach to the development of a multi-syntax programming language compiler. The technique of compiler parsing is based on the existing flex and bison specifications. The proposed approach makes it easier to detect errors in multi-syntax N-version software solutions, as well as reduce the likelihood of their occurrence due to the use of an automated tool, which is crucial for its implementation in an industrial setting.
D. Fortuné KPONOU, Salima Mdhaffar, Fréjus A. A. Laleye, Eugène Cokou Ezin, Yannick Estève. Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025). 2025.