This user has not added any information to their profile yet.
I received my BSc and MSc from the Computer Science Department of the University of Crete in 2012 and 2014 respectively. From 2011 until 2014, I had been a research assistant at the Signal Processing Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas. In 2014, I was an intern at TOSHIBA, Cambridge Research Laboratory - Speech Technology Group. From 2015 until 2016, I worked as an R&D engineer at the Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas.
For my PhD project, I am investigating the impact of different speech types, individual speech cues and maskers on listening effort, in native and non-native listeners.
Listeners' preferences might be used as an indicator of optimal listening and applied in the design of speech enrichment algorithms. We have developed a tool, called SpeechTuner, for acquiring listener preferences and intelligibility scores using a real-time speech feature controller as akin to choosing the appropriate volume on the TV or radio. This technique can be adapted readily to many scenarios such as different masking conditions and different speech features. Experiments with native normal-hearing listeners measured the consequences of allowing listeners to change spectral slope, the location of a spectral band of speech, speech rate and mean F0. Speech stimuli were presented in both quiet and masked conditions. As the noise level increased, compared to the original values, listeners (i) chose increasingly flatter spectral tilts; (ii) moved spectral bands to higher frequencies and (iii) preferred slower speech rates. However, the mean of F0 was unaffected by noise and was always lower than the original F0. These outcomes are largely consistent with earlier findings of the effect of corresponding modifications on intelligibility, but provide additional information in cases where intelligibility is at ceiling levels.
Furthermore, the impact of listening effort on different speech types has been examined within my project. A physiological measure of listening effort (pupil size), listeners’ subjective judgements as well as intelligibility measures, have been combined in order to examine the impact of four speech types: plain (natural) speech, speech produced in noise (Lombard speech), speech enhanced to promote intelligibility, and synthetic speech. Naturally and artificially modified speech were less effortful than plain speech at the more adverse noise levels. The outcomes indicated a clear impact of speech type on the cognitive demands required for comprehension.