Update of acoustic and language models is vital to maintain performance of automatic speech recognition (ASR) systems. To alleviate efforts for updating models, we propose a "...
Yuya Akita, Masato Mimura, Graham Neubig, Tatsuya ...
Most existing methods of semi-supervised clustering introduce supervision from outside, e.g., manually label some data samples or introduce constrains into clustering results. Thi...
A new adaptive multispectral image compression technique based on the regions identified is proposed. The algorithm is adaptive in the sense that according to the data type class ...
This paper argues for a special focus on the use of dynamic human interaction to explore datasets while they are being transformed into sound. We describe why this is a special ca...
Abstract. We describe a scalable parallel implementation of the self organizing map (SOM) suitable for datamining applications involving clustering or segmentation against large da...
Richard D. Lawrence, George S. Almasi, Holly E. Ru...