Fairfield, Connecticut
April 19, 2024
April 19, 2024
April 20, 2024
8
10.18260/1-2--45755
https://peer.asee.org/45755
66
Hammad Mansoor is a passionate programmer currently pursuing a Master's degree in Software Engineering at Fairfield University. He is a graduate assistant at the Fredrickson Family Innovation Lab. With a strong affinity for Python, he enjoys crafting elegant code and has gained valuable experience in applied machine learning. Outside of the digital world, he finds solace in the great outdoors and often explores nature through hiking.
Danushka Bandara received the bachelor’s degree in Electrical Engineering from the University of Moratuwa, Sri Lanka, in 2009. He received
his master’s and Ph.D. degrees in Computer Engineering and Electrical and Computer Engineering from Syracuse University, Syracuse, NY, USA, in
2013 and 2018, respectively. From 2019 to 2020, he worked as a Data Scientist at Corning Incorporated, Corning, NY, USA. Currently, he is an
Assistant Professor of Computer Science and Engineering at Fairfield University, Fairfield, CT, USA. His Current research interests include Applied machine learning, Bioinformatics, Human-computer interaction, and Computational social science.
Animal vocalizations provide a wealth of information on an animal and their surrounding environment. This acoustic data can help us understand the behavioral, physical and mental state of an animal, which can further help biologists better support the animal’s health and well being. Our project aims to create an automated process using which biologists can identify and annotate Leopard vocalizations from recordings made at animal enclosures. These annotations will be used to study correlations between vocal characteristics and estrus in leopards. Currently, each 24 hour recording takes upwards of 74 minutes to annotate and each clip has to be manually extracted from the main recording. This is a manual task that requires an individual to carefully go through the recording and verify instances of leopard calls. Our focus is therefore, not only to reduce this annotation time but also to better allocate resources on more pressing tasks. For this, we use ‘auditok’, an Audio Activity Detection tool to isolate sounds that are above a certain energy threshold and then store them as individual clips while also retaining timestamp information. Preliminary tests on denoised recordings reveal that most animal vocalizations last about 30 seconds and occur in groups of 15 - 20 individual calls. Using auditok and a Python pipeline, we are able to successfully isolate these individual calls and store them as clips. We also store start and end times for each vocalization on an excel sheet for reference. Currently, we are able to identify all instances of grouped calls and ~85% of individual calls within each group within 30 - 50 seconds per file.
Mansoor, H., & Bandara, D. (2024, April), Automating Annotations for Leopard Vocalizations Paper presented at 2024 ASEE North East Section, Fairfield, Connecticut. 10.18260/1-2--45755
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2024 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015