Cross-Dialect Bird Species Recognition with Dialect-Calibrated Augmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914058158997504 |
|---|---|
| author | Ding, Jiani Sun, Qiyang Akman, Alican Schuller, Björn W. |
| author_facet | Ding, Jiani Sun, Qiyang Akman, Alican Schuller, Björn W. |
| contents | Dialect variation hampers automatic recognition of bird calls collected by passive acoustic monitoring. We address the problem on DB3V, a three-region, ten-species corpus of 8-s clips, and propose a deployable framework built on Time-Delay Neural Networks (TDNNs). Frequency-sensitive normalisation (Instance Frequency Normalisation and a gated Relaxed-IFN) is paired with gradient-reversal adversarial training to learn region-invariant embeddings. A multi-level augmentation scheme combines waveform perturbations, Mixup for rare classes, and CycleGAN transfer that synthesises Region 2 (Interior Plains)-style audio, , with Dialect-Calibrated Augmentation (DCA) softly down-weighting synthetic samples to limit artifacts. The complete system lifts cross-dialect accuracy by up to twenty percentage points over baseline TDNNs while preserving in-region performance. Grad-CAM and LIME analyses show that robust models concentrate on stable harmonic bands, providing ecologically meaningful explanations. The study demonstrates that lightweight, transparent, and dialect-resilient bird-sound recognition is attainable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cross-Dialect Bird Species Recognition with Dialect-Calibrated Augmentation Ding, Jiani Sun, Qiyang Akman, Alican Schuller, Björn W. Sound Audio and Speech Processing Dialect variation hampers automatic recognition of bird calls collected by passive acoustic monitoring. We address the problem on DB3V, a three-region, ten-species corpus of 8-s clips, and propose a deployable framework built on Time-Delay Neural Networks (TDNNs). Frequency-sensitive normalisation (Instance Frequency Normalisation and a gated Relaxed-IFN) is paired with gradient-reversal adversarial training to learn region-invariant embeddings. A multi-level augmentation scheme combines waveform perturbations, Mixup for rare classes, and CycleGAN transfer that synthesises Region 2 (Interior Plains)-style audio, , with Dialect-Calibrated Augmentation (DCA) softly down-weighting synthetic samples to limit artifacts. The complete system lifts cross-dialect accuracy by up to twenty percentage points over baseline TDNNs while preserving in-region performance. Grad-CAM and LIME analyses show that robust models concentrate on stable harmonic bands, providing ecologically meaningful explanations. The study demonstrates that lightweight, transparent, and dialect-resilient bird-sound recognition is attainable. |
| title | Cross-Dialect Bird Species Recognition with Dialect-Calibrated Augmentation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.22317 |