VocADom@DOMUS

(in construction)

Context of the acquisitions

This corpus was recorded by the LIG laboratory (Laboratoire d’Informatique de Grenoble, UMR 5217 CNRS/UGA) thanks to the  VocADom project founded by the French National Research Agency (Agence Nationale de la Recherche/ANR-16-CE33-0006). The authors would like to thank the participants who accepted to perform the experiments.

This corpus is composed of audio and home automation data acquired in a real smart home with French speakers. This campaign was conducted within the VocADom project aiming at designing a new smart home system based on audio technology. The developed system provides assistance via natural man-machine interaction (voice and tactile command) and security reassurance by detecting distress situations so that the person can manage, from anywhere in the house, her environment at any time in the most natural way possible.

Home automation Smart Home of the LIG Laboratory

DOMUS smart apartment is part of the experimentation platform of the LIG laboratory and is dedicated for research projects.  According to the different research projects, experimentations are conducted with users performing scenarios of daily housework and leisure. Multimodal corpus are produced, synchronized and analyzed in order to evaluate and validate the concerned concept or system.

Appartment

DOMUS is a 35m2 apartment used to collect this dataset has the following layout (kitchen, bathroom, bedroom, living room):

Sensors

DOMUS is fully functional and equipped with sensors, such as energy and water consumption, level of hygrometry, temperature, and effectors able to control lighting, shutters, multimedia diffusion, distributed in the kitchen, the bedroom, the office and the bathroom. An observation instrumentation, with cameras, microphones and activity tracking systems, allows to control and supervise experimentations from a control room connected to Amiqual4Home. The flat also is equipped with 16 microphones (4 arrays of 4 microphones each) set into the ceiling that can be recorded in real-time thanks to a dedicated software able to record simultaneously the audio channels.

Description of the dataset

Grammar of the voice command

Scenarios

1. Phase 1:–
   1. 1. (2 persons) keywords, elicitation of vocal commands

   –

   1. 1. (1 person) free discovery of the vocal command system

   –

   1. 1. (2 persons) demonstration of the system to a naive participant (trainee)

   –

   1. (3 persons) interview with the experimenter
2. Phase 2:–
   1. 1. (4 persons) 2 technicians are coming in to maintain the system during an interview between the experimenter and the participant

   –

   1. (2 persons) technicians are going out and a risk situation is notified

Participants’ recordings (duration in the format hour:minute:second; AG=aged people, VI=visually impaired)

Data structure

Annotations