Effects of interpulse-interval variation on deep-learning classification of bat vocalizations

Welmoed R. Eversteijn; Burooj Ghani; A. Leonie Baier; Dan Stowell

cs.LGOct 1, 2026

Effects of interpulse-interval variation on deep-learning classification of bat vocalizations

Authors: Welmoed R. Eversteijn, Burooj Ghani, A. Leonie Baier, Dan Stowell

Organizations: Naturalis Biodiversity Centre, Darwinweg 2, Leiden, 2333 CR, The Netherlands · Department of Cognitive Science and Artificial Intelligence, Tilburg University, Warandelaan 2, Tilburg, 5037 AB, The Netherlands

Abstract

Temporal context may aid automated bat-species classification, but the contribution of specific features remains unclear. We investigated whether variation in the interpulse interval (IPI)-the time between consecutive call onsets-provides species-discriminative information and whether transformer-based models are more sensitive to this information than convolutional neural networks. We created two matched datasets from European bat recordings: a natural-IPI condition retaining the original call timing and a normalized-IPI condition in which call onsets were spaced at 50-ms intervals. EfficientNet-B0 and PaSST were fine-tuned and evaluated within each condition. In an additional experiment, each architecture was trained separately on natural-IPI and normalized-IPI recordings, and evaluated on the same natural-IPI test set. Finally, the pretrained classifiers BatDetect2 and BAT were evaluated on both conditions. Within-condition IPI normalization had model-dependent effects. PaSST accuracy differed little between the natural-IPI ( $71 \pm 2.3\%$ ) and normalized-IPI ( $70 \pm 6.3\%$ ) conditions, whereas EfficientNet accuracy increased from $47 \pm 4.7\%$ to $57 \pm 3.9\%$ . PaSST exceeded EfficientNet under both conditions. In the cross-condition evaluation, models trained on natural-IPI recordings outperformed those trained on normalized-IPI recordings on the natural-IPI test set: accuracy decreased from 54% to 50% for EfficientNet and from 65% to 57% for PaSST. BatDetect2 and BAT differed little between IPI conditions. Overall, we found limited support for the hypotheses that natural IPI variation contributes substantially to bat-species classification and that it is used more effectively by transformer-based than CNN-based models. Nevertheless, the cross-condition performance decrease shows that results obtained under normalized conditions may not transfer fully to natural recordings.

Figures & tables

Figure 1: Spectrogram of a bat echolocation sequence illustrating the temporal progression from search to approach and capture (terminal buzz), and the corresponding changes in call structure. Approximate frequency and time scales are included to provide a general sense of scale. The photographs illustrate the three behavioural phases; the depicted bat species differs from that of the echolocation sequence. Bat photographs: © Dietmar Nill, adapted and used with permission. The photographs are excluded from the Creative Commons license applicable to this article.

Experiment and purpose	Models	Training condition	Evaluation procedure
1. Within-condition evaluation Assess the effect of IPI normalization when training and evaluation use the same IPI condition	EfficientNet-B0 PaSST	Separate training on: (1) natural IPI; (2) normalized IPI	Five-fold stratified cross-validation was conducted within each condition: natural IPI $\rightarrow$ natural IPI; normalized IPI $\rightarrow$ normalized IPI.
2. Cross-condition evaluation Assess generalization from normalized to natural IPI	EfficientNet-B0 PaSST	Separate training on: (1) natural IPI; (2) normalized IPI	Models were evaluated on natural-IPI test recordings: natural IPI $\rightarrow$ natural IPI (baseline); normalized IPI $\rightarrow$ natural IPI.
3. Existing-model evaluation Assess whether IPI normalization affects predictions from existing classifiers	BatDetect2 BAT	No additional training; pretrained models were used	Models were evaluated on natural-IPI and matched normalized-IPI recordings. Performance was calculated for all 16 species and for only the species represented in each model’s original training data.

Table 1: Overview of the experimental design. Natural IPI refers to recordings retaining the original temporal spacing between calls; normalized IPI refers to recordings in which variation in the intervals between call onsets was reduced.

Species	Number of recordings	Total audio duration (sec)	BatDetect2 training set	BAT training set
Miniopterus schreibersii	21	42	–	✓
Barbastella barbastellus	20	40	✓	–
Eptesicus serotinus	20	40	✓	✓
Hypsugo savii	20	40	–	✓
Myotis capaccinii	20	40	–	✓
Myotis dasycneme	20	40	–	✓

Table 2: Number and total duration of recordings per species. Checkmarks indicate that the species was represented in the original training data of BatDetect2 or BAT.

Parameter	EfficientNet	PaSST
Backbone	CNN	Transformer
Model version	EfficientNet-B0	passt_s_f128_20sec_p16 _s10_ap.474_swa.pt
Pretraining	ImageNet	AudioSet
Input size	$3\times 128\times 1024$	$1\times 128\times 2000$
Clip duration	2 sec	20 sec
Sampling rate	250 kHz	32 kHz

Table 3: Model, preprocessing, and training configurations.

Figure 2: Classification accuracy across the three experiments. (A) Within-condition performance of EfficientNet-B0 and PaSST under the natural-IPI and normalized-IPI conditions. In each case, models were trained and validated on recordings from the same IPI condition using five-fold stratified cross-validation. (B) Cross- and matched-condition performance in Experiment 2. EfficientNet-B0 and PaSST were trained on normalized-IPI (left) and natural-IPI (right) recordings and evaluated on the same fixed test set with natural-IPI variation. Connected points show the change from training on normalized-IPI recordings (normalized $\rightarrow$ natural) to training on their natural-IPI counterparts (natural $\rightarrow$ natural). Experiment 2 was the only experiment in which models were evaluated under an IPI condition different from that used for training. (C) Performance of the existing pretrained classifiers BatDetect2 and BAT when evaluated without additional training on the natural-IPI and normalized-IPI datasets. Bars show results for the complete dataset and each model’s known-species subset.

Figure 3: Effect of IPI normalization on species-level F1-scores. Species-level F1-scores under the natural-IPI and normalized-IPI conditions are shown for EfficientNet-B0, PaSST, BatDetect2, and BAT (from left to right). For EfficientNet-B0 and PaSST, scores were obtained when each model was trained and evaluated within the same IPI condition. BatDetect2 and BAT were evaluated without additional training on both dataset conditions. Arrows indicate the change from the natural-IPI score to the normalized-IPI score for each species. Green right-pointing arrows denote an increase following IPI normalization, whereas red left-pointing arrows denote a decrease. Numerical labels report the corresponding change in F1-score in percentage points, calculated as normalized IPI minus natural IPI. In the BatDetect2 and BAT panels, an asterisk indicates a species that was not represented in the respective model’s original training data; asterisks do not indicate statistical significance.

Experiment / Model	Dataset Condition	Accuracy (%)	Macro F1-Score
Experiment 1: Within-Condition Cross-Validation
PaSST	Natural IPI	$71.0\pm 2.3$	0.68
PaSST	Normalized IPI	$70.0\pm 6.3$	0.67
EfficientNet-B0	Natural IPI	$47.0\pm 4.7$	0.43
EfficientNet-B0	Normalized IPI	$57.0\pm 3.9$	0.52
Experiment 2: Cross-Condition Generalization

Table 4: Classification performance across experimental conditions for custom-trained models and pretrained benchmark classifiers. Values represent accuracy or macro F1-score, as indicated. For Experiment 1, values are reported as the mean (

\pm

SD) across the five validation folds. Experiments 2 and 3 used single evaluation sets and are therefore reported without variability estimates.

Explore similar work

ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy
Aug 18, 2026Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum +4Classification Bioacoustics
Naturalis Biodiversity Center · Department of Cognitive Science and Artificial Intelligence, Tilburg University · People and Nature Lab, University College London +1
Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition
Sep 8, 2026Frank Fundel, Alexandra HowardPseudo-Labeling Bioacoustics
Ludwig-Maximilians-Universität München, Germany · University of the Free State, Department of Zoology and Entomology, Qwaqwa Campus, South Africa
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
Jun 11, 2026Olga Isupova, Danil Kuzin, Ella Browning +2Audio Representation Learning Audio Understanding
Leverhulme Centre for Nature Recovery, School of Geography and the Environment, University of Oxford, Oxford, UK

Aug 18, 2026J/K move · Enter open · S save

ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy

Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum, Juan Sebastián Cañas+3

Naturalis Biodiversity Center · Department of Cognitive Science and Artificial Intelligence, Tilburg University · People and Nature Lab, University College London+1

Classification Bioacoustics Wildlife Monitoring Open-Set Recognition Hierarchical Classification

Open paper AskPDF arXiv

Bats are key indicators of ecosystem health and are protected throughout Europe, making reliable population monitoring a conservation priority. Their cryptic nocturnal lifestyle makes passive acoustic monitoring essential, yet automated identification remains difficult as echolocation calls vary with behaviour and environment and overlap among species. We present a deep learning framework that jointly predicts species and genus and combines genus predictions with geographic species distributions at inference. When only one species of a predicted genus occurs in a region, the framework can resolve species absent from the learned taxonomy. This reframes geographic information as a means of extending, rather than constraining, a classifier's effective taxonomy. Using recordings spanning 35 European bat species, we evaluate closed-set classification, examine the instability of performance estimates for sparsely represented species, and conduct a controlled held-out proof-of-principle experiment. The rare-species analysis shows how limited evaluation data can obscure species-level performance, while the held-out experiment shows that genus predictions and location can recover labels unavailable to the species head. Geographic resolution extends operational coverage from 35 to 41 of the 48 native European bat species, increasing coverage from 73% to 85%. To our knowledge, this is the broadest operational coverage reported for automated European bat classification. More broadly, the bat framework provides proof of principle for resolving unseen fine-grained classes by combining coarse predictions with transparent external constraints.

Abstract

Explore similar work

ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy

Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition

Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier