One of the new working fields of the group is focussed on the audiology domain. The main purpose of this line of research is to serve as a support system for the evaluation of patients during the course of an audiometry. An audiometry is a typical hearing test to measure the hearing thresholds, and therefore, assess and diagnose the hearing of a patient.

Hearing tests require collaboration and interaction with the patient. To perform this test, the patient needs to wear some headphones connected to the audiometer. The expert will send pure tones at different intensities and frequencies through this device. Meanwhile, the patient should raise his hand anytime he notices the sound. The execution of these tests are videotaped for later analysis.

Besides the exploration of the hearing, during the performance of this test, experts subjectively could analyze the speed of response of the patient. An abnormally slow speed of response compared with the average response rate may be a sympton of cognitive problems or other diseases. We have developed a preliminary methodology that allows objective and accurate measurement of patient's speed of response by the automatic analysis of the video sequences recorded during the audiometries. These measurements allow the accurate and automatic identification of patients with abnormally slow response times, and they also allow the experts to carry out statistical studies or other assessments.

Next researchs will be oriented to the achievement of a system that allows the objective evaluation of patients with severe cognitive problems, usually associated with senile disorders. While these patients may not interact in a traditional way, they do exist subconscious reactions that affect the expression of their face and require a high degree of experience to be interpreted. The detection of significant changes in the facial expression and the correct interpretation of them will allow to identify them as a response to the auditory stimuli for this specific group of patients.


The VAST: Video Audiometry Sequence Test database is a set of video sequences of different patients recorded during the performance of the pure tone audiometry tests. The dataset includes a total of 11 video sequences with a duration ranging from 4 to 8 min. Video sequences were recorded in high resolution (1080x1920 pixels) with a frame rate of 25 FPS (frames per second). The scene of acquisition of the video sequences is quite simple, the video camera is located behind the audiologist (the audiologist is sitting in front of the patient) and the scene recorded shows the patient's face and the audiometer.

If you are interested in using the VAST video database, please send an email to: and you will receive an authentication password to access the database. This is intended for statistical purposes only, no private data or fee is required. If you use this image set for your work, please include a reference of VAST in it.


Faculty of Optics and Optometry.

Main publications

  • A. Fernández, M. Ortega, B. Cancela, M. G. Penedo, C. Vazquez, LM Gigirey, "Automatic processing of audiometry sequences for objective screening of hearing loss", Expert Systems with Applications, DOI 10.1016/j.eswa.2012.05.015, 2012. (pending of publication).
    [Abstract] [PDF]
  • A. Fernández, M. Ortega, B. Cancela, M. G. Penedo, C. Vazquez, LM Gigirey, "Measuring response times to auditory stimuli during an audiometry", 4th International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2011), Barcelona, Spain, October 2011.
    [Abstract] [PDF] [+Info.]
  • A. Fernández, M. Ortega, M. G. Penedo, B. Cancela, LM Gigirey, C. Vazquez, "Automatic analysis of the patient's conscious responses to the emission of auditory stimuli during the performance of an audiometry", International Conference on Digital Image Computing: Techniques and Applications (DICTA), 291-296, Noosa, Australia, December 2011.
    [Abstract] [PDF] [+Info.]