No abstract

Voice control is an important function in many mobile devices, in a smart home, especially in providing people with disabilities a convenient way to communicate with the device. Despite many studies on this problem in the world, there has not been a formal study for the Vietnamese language. In addition, many studies did not offer a solution that can be expanded easily in the future. During this study, a dataset of Vietnamese speech commands is labeled and organized to be shared with community of general language research and Vietnamese language study in particular. This paper provides a speech collection and processing software. This study also designs and evaluates Recurrent Neural Networks to apply it to the data collected. The average recognition accuracy on the set of 15 commands for controlling smart home devices is 98.19%.

Recommendation systems based on convolutional neural network (CNN) have attracted great attention due to their effectiveness in processing unstructured data such as images or audio. However, a huge amount of raw data produced by data crawling and digital transformation is structured, which makes it difficult to utilize the advantages of CNN. This paper introduces a novel autoencoder, named Half Convolutional Autoencoder, which adopts convolutional layers to discover the high-order correlation between structured features in the form of Tag Genome, the side information associated with each movie in the MovieLens 20 M dataset, in order to generate a robust feature vector. Subsequently, these new movie representations, along with the introduction of users’ characteristics generated via Tag Genome and their past transactions, are applied into well-known matrix factorization models to resolve the initialization problem and enhance the predicting results. This method not only outperforms traditional matrix factorization techniques by at least 5.35% in terms of accuracy but also stabilizes the training process and guarantees faster convergence.

No abstract

No abstract