arXiv subjects

Hatice Gunes

Publications and source records attributed to Hatice Gunes.

92 records · Page 6Linked to original sources

arXiv2018

An empirical approach to the relationship between emotion and music production quality

In music production, the role of the mix engineer is to take recorded music and convey the expressed emotions as professionally sounding as possible. We investigated the relationship between music production quality and musically induced and perceived emotions. A listening test was performed where 10 critical listeners and 10 non-critical listeners evaluated 10 songs. There were two mixes of each song, the low quality mix and the high quality mix. Each participant's subjective experience was measured directly through questionnaire and indirectly by examining peripheral physiological changes, change in facial expressions and the number of head nods and shakes they made as they listened to each mix. We showed that music production quality had more of an emotional impact on critical listeners. Also, critical listeners had significantly different emotional responses to non-critical listeners for the high quality mixes and to a lesser extent the low quality mixes. The findings suggest that having a high level of skill in mix engineering only seems to matter in an emotional context to a subset of music listeners.

eess.IV↗

arXiv2015

Face Alignment Assisted by Head Pose Estimation

In this paper we propose a supervised initialization scheme for cascaded face alignment based on explicit head pose estimation. We first investigate the failure cases of most state of the art face alignment approaches and observe that these failures often share one common global property, i.e. the head pose variation is usually large. Inspired by this, we propose a deep convolutional network model for reliable and accurate head pose estimation. Instead of using a mean face shape, or randomly selected shapes for cascaded face alignment initialisation, we propose two schemes for generating initialisation: the first one relies on projecting a mean 3D face shape (represented by 3D facial landmarks) onto 2D image under the estimated head pose; the second one searches nearest neighbour shapes from the training set according to head pose distance. By doing so, the initialisation gets closer to the actual shape, which enhances the possibility of convergence and in turn improves the face alignment performance. We demonstrate the proposed method on the benchmark 300W dataset and show very competitive performance in both head pose estimation and face alignment.

cs.CV↗