BattyBirdNET has been a useful tool for some, but I think it is fairly limited on species.

We tend to just use the BTO pipeline, as they offer a lot of small mammals and moths as well.

Read "GitHub - rdz-oss/BattyBirdNET-Analyzer: BattyBirdNET analyzer for scientific audio data processing." on GitHub

GitHub - rdz-oss/BattyBirdNET-Analyzer: BattyBirdNET analyzer for scientific audio data processing.

BattyBirdNET analyzer for scientific audio data processing. - rdz-oss/BattyBirdNET-Analyzer

GitHub

We also donate some money to the acoustic pipeline from our sales, so I have a vested interest!

There are others who have made a lot of cool add-ons to birdnet, but fundamentally you may have an issue when it comes to ultrasonic.

I would be interested to hear more!

Hi Danielle,

I have had success in training custom classifiers using BirdNET for Southeast Asian primates, and I'm working to get this research published soon-ish. My main advice would be to have a robust subset of non-target sounds (you can do this by adding a "NOISE" folder), ESPECIALLY from audio data that is from your study site of interest. Any vocalization toward the lower frequencies was more likely to potentially assign things like insect buzzing as detections. I worked iteratively assessing where the model was having issues with false detections. The model was also not performing great as a single-species classifier (even with non-target sounds), but really benefited from the addition of other species specifically occupying a similar frequency range. 

BirdNET is great at offering tools for assessing model performance with the "SEGMENTS" feature. This allows you to get a probability cut-off with the confidence score (which will vary for each species), where you can see at what score there is a decent certainty of getting a correct detection. I did do some playing around with the parameters, but ultimately found that most of the default settings performed the best without overfitting. 

As far as getting examples of your species of interest, a lot of the free pattern matching tools will suffice with just one example of your target vocalization. I used the Arbimon platform for this purpose. The success you will have from this will ultimately depend on how rare your species of interest is, and how complex their vocalization is. Overall though, I found it much more preferable to parse through a lot of false detections like this than manually scan thousands of hours of recordings. If you have any other questions, feel free to reach out!

Hi! I’ve used BirdNet to train a model for detecting dugong vocalizations. We categorized the data into five distinct dugong call types and added an additional class for background noise (non-dugong sounds). I implemented a custom classifier. From my experience, I recommend carefully curating the training dataset by selecting only medium to high-quality recordings. Additionally, I ensured that only complete calls that represented the fundamental structure of each vocalization were included. This approach helped improve model accuracy and robustness.

@Retro Bowl I have trained BirdNet to detect additional species beyond those originally included in the model. My approach involved curating a custom dataset with labeled audio samples of target species, ensuring high-quality recordings with minimal background noise. I used transfer learning to fine-tune the BirdNet model with this dataset, adjusting parameters to optimize detection accuracy. For software workflow, I pre-processed the audio files to match BirdNet’s expected input format, used a spectrogram-based analysis for feature extraction, and employed TensorFlow for model retraining. While my main focus has been on birds not represented in the default model, I have also experimented with detecting anurans and certain insect species with promising results. I haven’t personally worked with bats, but I’ve seen research suggesting that adapting BirdNet for bat calls is possible with sufficient high-frequency data and modifications to the model’s training parameters.