Keizo Oyama
YOU?
Author Swipe
View article: An Iterative Linear Matrix Inequality Approach to Time-Synchronized Control for Spacecraft Stabilization Subject to Model Uncertainty and External Disturbance
An Iterative Linear Matrix Inequality Approach to Time-Synchronized Control for Spacecraft Stabilization Subject to Model Uncertainty and External Disturbance Open
This paper proposes an efficient parameter design approach for time-synchronized control in the spacecraft attitude stabilization problem. Existing studies on time-synchronized control typically demonstrate robustness only against external…
View article: Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training
Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training Open
Generating melody from lyrics is an interesting yet challenging task in the area of artificial intelligence and music. However, the difficulty of keeping the consistency between input lyrics and generated melody limits the generation quali…
View article: Applying Existing Datasets as a Pseudo Corpus for Sentiment Representation on Social Media
Applying Existing Datasets as a Pseudo Corpus for Sentiment Representation on Social Media Open
This paper proposes a method to represent the sentiment characteristics of opinions on social media by using some datasets as a pseudo corpus without any annotations. The widespread social media enables us to easily share our own opinions …
View article: MusicTM-Dataset for Joint Representation Learning among Sheet Music, Lyrics, and Musical Audio
MusicTM-Dataset for Joint Representation Learning among Sheet Music, Lyrics, and Musical Audio Open
This work present a music dataset named MusicTM-Dataset, which is utilized in improving the representation learning ability of different types of cross-modal retrieval (CMR). Little large music dataset including three modalities is availab…
View article: Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics
Unsupervised Generative Adversarial Alignment Representation for Sheet music, Audio and Lyrics Open
Sheet music, audio, and lyrics are three main modalities during writing a song. In this paper, we propose an unsupervised generative adversarial alignment representation (UGAAR) model to learn deep discriminative representations shared acr…
View article: Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval
Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval Open
Cross-modal retrieval aims to retrieve data in one modality by a query in another modality, which has been a very interesting research issue in the field of multimedia, information retrieval, and computer vision, and database. Most existin…
View article: Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA
Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA Open
Deep learning has successfully shown excellent performance in learning joint representations between different data modalities. Unfortunately, little research focuses on cross-modal correlation learning where temporal structures of differe…
View article: Personalized Music Recommendation with Triplet Network
Personalized Music Recommendation with Triplet Network Open
Since many online music services emerged in recent years so that effective music recommendation systems are desirable. Some common problems in recommendation system like feature representations, distance measure and cold start problems are…
View article: Deep Learning of Human Perception in Audio Event Classification
Deep Learning of Human Perception in Audio Event Classification Open
In this paper, we introduce our recent studies on human perception in audio event classification. In particular, the pre-trained model VGGish is used as feature extractor to process audio data, and DenseNet is trained by and used as featur…
View article: Deep Learning of Human Perception in Audio Event Classification
Deep Learning of Human Perception in Audio Event Classification Open
In this paper, we introduce our recent studies on human perception in audio event classification by different deep learning models. In particular, the pre-trained model VGGish is used as feature extractor to process audio data, and DenseNe…