|
|
|
|
|
Mohammed Saïd Kasttet, Abdelouahid Lyhyaoui, Douae Zbakh, Adil Aramja and Abderazzek Kachkari
Recently, artificial intelligence and data science have witnessed dramatic progress and rapid growth, especially Automatic Speech Recognition (ASR) technology based on Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs). Consequently, new end-to-...
ver más
|
|
|
|
|
|
|
|
|
|
|
Juan Carlos Atenco, Juan Carlos Moreno and Juan Manuel Ramirez
In this work we present a bimodal multitask network for audiovisual biometric recognition. The proposed network performs the fusion of features extracted from face and speech data through a weighted sum to jointly optimize the contribution of each modali...
ver más
|
|
|
|
|
|
|
|
|
|
|
Sen Du, Hong Zhu, Guangfeng Lin, Dong Wang and Jing Shi
Automatically describing the content of an image is a challenging task that is on the edge between natural language and computer vision. The current image caption models can describe the objects that are frequently seen in the training set very well, but...
ver más
|
|
|
|
|
|
|
|
|
|
|
Ju-Sang Lee, Joon-Choul Shin and Choel-Young Ock
Natural language models brought rapid developments to Natural Language Processing (NLP) performance following the emergence of large-scale deep learning models. Language models have previously used token units to represent natural language while reducing...
ver más
|
|
|
|
|
|
|
|
|
|
|
Ana Bárbara Cardoso, Bruno Martins and Jacinto Estima
This article describes a novel approach for toponym resolution with deep neural networks. The proposed approach does not involve matching references in the text against entries in a gazetteer, instead directly predicting geo-spatial coordinates. Multiple...
ver más
|
|
|
|
|
|
|
|
|
|
|
Arda Tezcan, Bram Bulté and Bram Vanroy
We identify a number of aspects that can boost the performance of Neural Fuzzy Repair (NFR), an easy-to-implement method to integrate translation memory matches and neural machine translation (NMT). We explore various ways of maximising the added value o...
ver más
|
|
|
|
|
|
|
|
|
|
|
Xiaodong Wang, Yining Zhao, Haili Xiao, Xiaoning Wang and Xuebin Chi
Logs record valuable data from different software and systems. Execution logs are widely available and are helpful in monitoring, examination, and system understanding of complex applications. However, log files usually contain too many lines of data for...
ver más
|
|
|
|
|
|
|
|
|
|
|
Yong Sun, Min Ji, Fengxiang Jin and Huimeng Wang
As air users, the public is also participants in air pollution control and important evaluators of environmental protection. Therefore, understanding the public perception and response to air pollution is an essential part of improving air governance. Th...
ver más
|
|
|
|
|
|
|
|
|
|
|
Aneta R. Borkowska, Beata Daniluk and Katarzyna Adamczyk
Multiple sclerosis (MS) is a progressive chronic disease of the Central Nervous System (CNS). Cognitive decline occurs rather rarely in relapsing?remitting multiple sclerosis (RRMS) compared to other types. The present study aimed to assess executive fun...
ver más
|
|
|
|
|
|
|
|
|
|
|
I Made Agus Wirawan,Ida Bagus Made Ludy Paryatna
Pág. pp. 15 - 30
Although the learning media of the Anggah Ungguhing Balinese language has been done anytime and anywhere through a mobile application, this application has several obstacles. In detail, the contributions of this study are: 1) to develop a dictionary appl...
ver más
|
|
|
|
|
|