Automatically writing stylized Chinese characters is an attractive yet challenging task due to its wide applicabilities. In this paper, we propose a novel framework named Style-Aware Variational Auto-Encoder (SA-VAE) to flexibly generate Chinese characters. Specifically, we propose to capture the different characteristics of a Chinese character by disentangling the latent features into content-...

In this paper a document analysis tool for historical manuscripts is proposed. The goal is to automatically segment layout components of the page, that is text, pictures and decorations. We specifically focused on the pictures, proposing a set of visual features able to identify significant pictures and separating them from all the floral and abstract decorations. The analysis is performed by b...

In this paper, a feature vector called the Enhanced Pitch Class Profile (EPCP) is introduced for automatic chord recognition from the raw audio. To this end, the Harmonic Product Spectrum is first obtained from the DFT of the input signal, and then an algorithm for computing a 12-dimensional pitch class profile is applied to it to give the EPCP feature vector. The EPCP vector is correlated with...

We explore the impact of including hue in a feature construction algorithm for colour target detection. Hue has a long standing record as a good attribute in colour segmentation, so it is expected to strengthen features generated by only RGB. Moreover, it may open the door to infer compact feature maps for skin detection. However, contrary to our expectations, those new features where hue parti...

We describe a system that can listen to a performance of Indian music and recognize the raag, the fundamental melodic framework that Indian classical musicians improvise within. In addition to determining the most likely raag being performed, the system displays the estimated the likelihood of each of the other possible raags, visualizing the changes over time. The system computes the pitch-cla...

fMPE is a previously introduced form of discriminative training, in which offsets to the features are obtained by training a projection from a high-dimensional feature space based on posteriors of Gaussians. This paper presents recent improvements to fMPE, including improved high-dimensional features which are easier to compute, and improvements to the training procedure. Other issues investiga...

To improve the performance of subspace classi er, it is e ective to reduce the dimensionality of the intersections between subspaces. For this purpose, the feature space is mapped implicitly to a high dimensional reproducing kernel Hilbert space and the subspace classi er is applied in this space. As a result of Hiragana recognition experiment, our classi er outperformed the conventional subspa...

This paper studies how prosodic features can help in the automatic detection of alcoholic intoxication. We compute features that have recently been proposed to model speech rhythm such as the pair-wise variability index for consonantal and vocalic segments (PVI) and study their aptness for the task. Further, we use a large prosodic feature vector modelling the usual candidates – pitch, intensit...

We develop a general feature space for automatic classification of verbs into lexical semantic classes. Previous work was limited in scope by the need for manual selection of discriminating features, through a linguistic analysis of the target verb classes (Merlo and Stevenson, 2001). We instead analyze the classification structure at a higher level, using the possible defining characteristics ...