Contrastive Ecoacoustic Indices: large-scale global soundscape characterization with contrastive inference

This archive has a companion paper entitled : Contrastive Ecoacoustic Indices: large-scale global soundscape characterization with contrastive inference, Methods in Ecology and Evolution, 2026

Abstract of the paper:

Ecoacoustics mainly aims at monitoring soundscapes by means of non-invasive protocols. Despite the widespread adoption of machine and deep learning techniques, existing ecoacoustic models predominantly rely on supervised learning and, consequently, face two primary limitations: (1) the necessity of annotated data; and (2) the restriction to fixed predefined classes. 

In this work, we leverage recent advances in Contrastive Language-Audio Pre-training (CLAP) and envision its first application to large-scale soundscape analysis. As trained on extensive datasets of paired audio and global text descriptions using contrastive learning, CLAP allows computing similarity scores between audio and text prompts without the constraints of predefined categorical lists. This flexibility enables a comprehensive investigation of various elements within the recordings from coarse-grained (e.g., mammals, weather, humans, vehicles) to fine-grained (e.g. dog, rain, speech, airplane) descriptions. 

Here, we first conducted a preliminary experiment on a calibration dataset, featuring audio events likely to occur in soundscapes, which is shared with the community and constituted from an online, free sound library. Then, we developed a methodology to define reproducible, bounded, independent, and interpretable Contrastive Ecoacoustic Indices (CEI), which can characterize the prevalence of four primary sound categories in soundscapes — biophony, geophony, anthropophony, and technophony. 

We finally computed these new CEI on 9-month field recordings (189,137 1-min excerpts) monitoring both tropical (Ecuador) and temperate (France) soundscapes, portraying an anthropic gradient from protected forests to urban city centers. This experiment reveals clear soundscape patterns associated with human population density suggesting that the CEI could be used in other ecological contexts.}

The archive contains :

• The complete supporting code to extract audio embeddings, compute audio-text similarities and obtain the CEI. Results can be saved into csv files and plotted as png figures.
• A complete executable run_cei.sh, encompassing all above-mentioned steps, as well as a Jupyter notebook, showcasing an example of usage, are also included.
• Data to run a quick test