We just updated our paper “A Bird Song Detector for improving bird identification through Deep Learning: a case study from Doñana”, officially accepted in Ecological Informatics 📍 Doñana National Park 📊 Passive Acoustic Monitoring 🤖 YOLOv8 + BirdNET 📰

@GrunCrow

I'm thrilled to share with you our lattest publication with the brilliant @GrunCrow as the first author. We propose here a two-stage pipeline for analyzing audios from a acoustic monitoring programme in Doñana; 1) using a detector of vocalizations, 2) a fine-tuned classificator.

First week of June I went to the SIBECOL & AEET meeting in Pontevedra I presented advances from #SEANIMALMOVE on using ecoacoustics for bird & marine mammal monitoring Some results are saved for upcoming papers — but the talk still won Best Multidisciplinary Predoc Oral Comm!

All data and methods are shared and publicly available: 📰Paper: https://t.co/jKr1OfTh3V 📁Dataset: https://t.co/2T6hjQnXX5 🤖Simplified Repository: https://t.co/xLRgu3TglB 🤖Main Repository:

General models like BirdNET are powerful, but local adaptation is key, but sometimes even fine-tuning or custom classifiers are not enough. By separating detection and classification, we boost precision and reduce noise in PAM workflows.

We also checked and compared BirdNET as a detector with our Bird Song Detector, our detector detected more birds with fewer false positives. 📷 FNs dropped 67% 📷 FPs stayed under 5%

The main innovation is that we trained a YOLOv8-based Bird Song Detector to filter only segments with bird vocalizations before running species classifiers. The results are that for all classifiers, metrics improve when the Bird Song Detector is first applied:

🎙️461 minutes manually annotated 📊3,749 annotated vocalizations (Frequency + Time of vocalization) 🐦34 classes (29 species-specific) It took 224 hours to annotate this data. For our Bird Song Detector we only used temporal annotations. 📁 https://t.co/2T6hjQnXX5

While BirdNET works well globally, it struggles with local soundscapes, especially in noisy, unfocused recordings — leading to many false positives. We propose a pipeline that starts with a Bird Song Detector to isolate vocalizations before classification.

Doñana is a biodiversity hotspot and a key stopover for millions of migratory birds. Monitoring this ecosystem is critical — but analyzing thousands of hours of audio isn’t easy. That’s where the intersection of Ecology and AI happens. And where BIRDeep team have been working

Alba Márquez-Rodríguez (@GrunCrow) has done an amazing work developing a Bird Song Detector. Many audios are empty or present overlapping bird songs. Previously applying a detector allows to select audios with songs, lower confidence score and improving classifications.

Thanks to the entire team, and specially to Irene Mendoza (@phenogirl ) for her invaluable support throughout this adventure It’s been an incredible experience applying AI to bioacoustics and conservation. From fieldwork in Doñana to the training of AI models🌍🎶

Our preprint "A Bird Song Detector for Improving Bird Identification through Deep Learning: A Case Study from Doñana" is now available! 🐦📢 🔗 https://t.co/YXn95OTJrQ This work is result of my JAE Intro fellowship, where I contributed to the #BIRDeep project at @ebdonana

I don’t use this social media much, but I’m moving to Mastodon to join my fellow scientists and friends. You can now find me there: https://t.co/8sGwNYQ3MR

@FCC_UCA @Divulga_UCA @univcadiz @campusdelmar La comunicación oral que presentaron fue “From prediction to accuracy in the validation of BirdNET in acoustic identification of birds in local ecosystems”.

🐟 La investigadora Alba Márquez presentó el proyecto #SEANIMALMOVE el pasado día 24 en las en las I Jornadas de Ecoinformática de la AEET, celebradas en Alcalá de Henares (Madrid) #inmar #investigación #congresos #divulgación @FCC_UCA @Divulga_UCA @univcadiz @campusdelmar

Damos comienzo a las I Jornadas de Ecoinformática de la AEET con foto de grupo y una excelente ponencia inaugural de @AnaBayes 🙂

Very inspiring the @ecoinf_aeet seminar by @antonalvarezbc & @PolskaCrow @_AEET_ https://t.co/zt1j2DWeHv

Alba Márquez @GrunCrow gave an outstanding talk at #ecoacoustics24 presenting a bird song detector that she has developed during her MSc thesis using #BIRDeep data. The idea is to detect first bird songs in audio and classify later those selected audios with @BirdNET_App.