Search

With the expansion of online financial services due to the use of mobile phones, stores, stores and branches are closing. Banks are also reducing offline business networks and reorganizing the financial transaction environment through mobile banking. However, financial transactions are inconvenient for the elderly, who do not use online services. In this paper, multimodal AI technology is utilized for senior-friendly services in mobile banking apps. Research UI/UX aspects of mobile banking apps and present prototypes. Two authentication modes are used for non-face-to-face identity verification using multimodal AI technology: visual (face verification) and auditory (speaker verification). For face identification, we use the FaceMash ML solution based on the Mediapipe framework, and for speaker identification, we use d-vector, a speech feature extraction method, in a deep learning DNN model. If multimodal AI technology is reflected, it will be possible to realize a convenient and safe senior-friendly use environment and contribute to the development of senior citizens' financial capabilities. [ABSTRACT FROM AUTHOR]

While foreigners' interest in learning Korean is increasing, the pronunciation evaluation technology provided through open API does not sufficiently consider the characteristics of foreign speech, so the reliability of the evaluation score is low. In this paper, we present a technique to supplement the existing pronunciation evaluation method by scoring the morphological relationship through the similarity analysis of the original text and the utterance result using voice recognition for foreigners' Korean speech. In order to determine the similarity between the original sentence and the sentence pronounced by a foreigner, a morpheme dictionary was created based on voice recognition and morpheme analysis, and then the similarity was measured using various distance measurement algorithms. As a result of the experiment, it was confirmed that the proposed method provides a score similar to the result that Koreans actually heard and recognized when compared with the existing foreigner speech evaluation model. [ABSTRACT FROM AUTHOR]

With the popularization of PC, SNS and IoT, a lot of data is generated and the amount is increasing exponentially. Artificial neural network learning is a topic that attracts attention in many fields in recent years by using huge amounts of data. Artificial neural network learning has shown tremendous potential in speech recognition and image recognition, and is widely applied to a variety of complex areas such as medical diagnosis, artificial intelligence games, and face recognition. The results of artificial neural networks are accurate enough to surpass real human beings. Despite these many advantages, privacy problems still exist in artificial neural network learning. Learning data for artificial neural network learning includes various information including personal sensitive information, so that privacy can be exposed due to malicious attackers. There is a privacy risk that occurs when an attacker interferes with learning and degrades learning or attacks a model that has completed learning. In this paper, we analyze the attack method of the recently proposed neural network model and its privacy protection method. [ABSTRACT FROM AUTHOR]