A monophonic cow sound annotation tool using a semi-automatic method on audio/video data
Yagya Raj Pandeya, Bhuwan Bhattarai, Usman Afzaal, Jong-Bok Kim, Joonwhoan Lee · Livestock Science · 2022
In this paper, we present a semiautomatic tool for labeling monophonic sound events with specific reference to cow sounds. The proposed system takes as input audio or video data and automatically suggests users possible event areas through spectral audio representation. Based on the system suggestions, users can quickly designate the temporal onset and offset points for audio events or even make new annotations. This tool gives users the ability to access audio and video signals at random from the waveform audio representation and to describe sounds in terms of emotional states and environmental conditions. The program is also able to detect incidents of mislabeling in the annotation process. Users can manually check and correct previous annotations using the corresponding visual and audio representations. The annotation output is exported as plain text data which is not in need of additional post processing by any other software. We tested our annotation tool on cow sound samples collected in raw audio and video formats from a cowshed and the Internet. In comparison to existing sound labeling programs, our proposed system is simple, semiautomatic, visually transparent, and faster.