Datasets

Smartphone-based ultrasonic dataset

This is a dataset of ultrasonic audio signals emitted and acquired with a Nexus 5 Android phone. Approximately 90 minutes (a total of more than 17600 pings) of ultrasonic recordings have been collected equally divided in two classes: ”Indoor” and ”Outdoor”. The recordings have been collected both in the case the phone was laying on a table and in the case the phone was held by a walking or stationary user.

It can be downloaded here.

Reference publication:
Igor Bisio, Alessandro Delfino, Fabio Lavagetto, “A simple ultrasonic Indoor/Outdoor detector for mobile devices” , Proc. International Wireless Communications & Mobile Computing Conference (IWCMC 2015), August 24-27, 2015, Dubrovnik, Croatia.

Smartphone-based accelerometer dataset

This is a dataset of accelerometric sample acquired for Activity Recognition (AR) and Movement Recognition (MR) algorithm. We collected raw measurements (one for each Cartesian axis: x, y, z). Since our algorithm required the framing of the signals, the frame duration has been set equal to 4 s. For the Activity Recognition (AR) case a set of about 14 hours has been employed. Acquisitions were performed by 8 users who kept the smartphones in four different positions and orientations: a) facing towards the user, b) towards the opposite side, c) pointing up, d) pointing down. For the Movement Recognition (MR) case the employed set consists of about 1500 accelerometer signals (corresponding to about 2 hours). Such signals have been acquired by 6 users who have kept the smartphones in their right hand when they performed the movements, independently of the devices orientation. The whole database (AR and MR), already exported in Matlab environment, is downloadable and available for possible further experiments and comparisons.

It can be downloaded here.

Reference publication:
I. Bisio, A. Delfino, F. Lavagetto, A. Sciarrone, “Enabling IoT for In-Home Rehabilitation: Accelerometer Signals Classification Methods for Activity and Movement Recognition" , IEEE Internet of Things Journal, doi: 10.1109/JIOT.2016.2628938.

Smartphone-based human speeches dataset

Dataset 1

This is a dataset of human speeches (both male and female) acquired with smartphones. It consists in a set of clean audio signals belonging to different speakers producing utterances in Italian language. For each known speaker 25 audio files have been acquired, while 41 files are related to unknown speakers. Consequently, the overall audio database consists of 141 files divided into 30 female and 111 male speeches.

It can be downloaded here.

Reference publication:

I. Bisio, C. Garibotto, F. Lavagetto, and A. Sciarrone, “Speaker Recognition Exploiting D2D Communications Paradigm: Performance Evaluation of Multiple Observations Approaches”, Journal of Mobile Networks and Applications (MONET), 2017.

Disclaimer

Datasets, software and multimedia material downloaded from the DSP Lab web site is provided 'as is' without warranty of any kind, either express or implied, including, but not limited to, the implied warranties of fitness for a purpose, or the warranty of non-infringement. Without limiting the foregoing, the DSP Lab staff makes no warranty that: i) the downloaded material will meet your requirements; ii) the downloaded material will be uninterrupted, timely, secure or error-free; iii) the results that may be obtained from the use of our material will be effective, accurate or reliable iv) the quality of the software will meet your expectations.

Software and its documentation made available on the DSP Lab web site: i) could include technical or other mistakes, inaccuracies or typographical errors; ii) the DSP Lab may make changes to the software or documentation made available on its web site; iii) may be out of date; DSP Lab assumes no responsibility for errors in the software or documentation available from its web site.

In no event shall the DSP Lab be liable to you or any third parties for any special, punitive, incidental, indirect or consequential damages of any kind, or any damages whatsoever, including, without limitation, those resulting from loss of use, data or profits, whether or not the DSP Lab has been advised of the possibility of such damages, and on any theory of liability, arising out of or in connection with the use of this software.

The use of the material downloaded through the DSP Lab site is done at your own discretion and risk and with agreement that you will be solely responsible for any damage to your computer system or loss of data that results from such activities. No advice or information, whether oral or written, obtained by you from the DSP Lab or from the DSP Lab web site shall create any warranty for the software.