Semi-Automated Annotation of Audible Home Activities
Autor: | Joseph Rafferty, Jesus Favela, Jessica Beltran-Marquez, Irvin Hussein Lopez-Nava, Dagoberto Cruz-Sandoval, Jonathan Synnott, Andrew Ennis, Chris D. Nugent, Netzahualcoyotl Hernandez-Cruz, Ian Cleland, Matias Garcia-Constantino |
---|---|
Rok vydání: | 2019 |
Předmět: |
Computer science
Feature extraction Intelligent decision support system 020206 networking & telecommunications 02 engineering and technology Work in process Data modeling Activity recognition Annotation Human–computer interaction 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Hidden Markov model Classifier (UML) |
Zdroj: | PerCom Workshops |
Popis: | Data annotation is the process of segmenting and labelling any type of data (images, audio or text). It is an important task for producing reliable datasets that can be used to train machine learning algorithms for the purpose of Activity Recognition. This paper presents the work in progress towards a semi-automated approach for collecting and annotating audio data from simple sounds that are typically produced at home when people perform daily activities, for example the sound of running water when a tap is open. We propose the use of an app called ISSA (Intelligent System for Sound Annotation) running on smart microphones to facilitate the semi-automated annotation of audible activities. When a sound is produced, the app tries to classify the activity and notifies the user, who can correct the classification and/or provide additional information such as the location of the sound. To illustrate the feasibility of the approach, an initial version of ISSA was implemented to train an audio classifier in a one-bedroom apartment. |
Databáze: | OpenAIRE |
Externí odkaz: |