This research focuses on developing an innovative machine learning-based approach to identify bird species through sound classification using Gammatone Frequency Cepstral Coefficients (GTCC) and YAMNet filtering. The proposed approach aims to analyze bird vocalizations by extracting relevant acoustic features and applying machine learning techniques to distinguish different types of bird sounds accurately and efficiently.
By combining GTCC-based feature extraction with YAMNet-based filtering, the research seeks to enhance the processing, identification, and classification of bird audio signals, particularly in environments containing various background noises. The integration of these technologies offers a promising approach to improving automated acoustic monitoring and supporting more efficient wildlife observation.
Furthermore, this research has potential applications in biodiversity conservation, ecological monitoring, and the development of intelligent systems for identifying bird species in their natural habitats. The findings are expected to contribute to technological advancements in environmental research while supporting sustainable biodiversity management and wildlife conservation efforts, particularly in alignment with Sustainable Development Goal 15 (SDG 15) – Life on Land.