Cross-Dialect Bird Species Recognition with Dialect-Calibrated Augmentation

2025/09/26 by Ding, Jiani, Sun, Qiyang, Akman, Alican +1
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2509.22317

Abstract

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.

Citations

• First-of-its-kind AI model for bioacoustic detection using a lightweight associative memory Hopfield neural network
• Detecting Machine-Generated Music with Explainability -- A Challenge and Early Benchmarks
• Explainable Artificial Intelligence for Medical Applications: A Review
• Audio-based Kinship Verification Using Age Domain Conversion
• DB3V: A Dialect Dominated Dataset of Bird Vocalisation for Cross-corpus Bird Species Recognition
• AudioProtoPNet: An interpretable deep learning model for bird sound classification
• Improving Domain Generalization for Sound Classification with Sparse Frequency-Regularized Transformer
• Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
• LEAF: A Learnable Frontend for Audio Classification
• Group Whitening: Balancing Learning Efficiency and Representational Capacity
• PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
• CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion
• mixup: Beyond Empirical Risk Minimization
• A Unified Approach to Interpreting Model Predictions
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Unsupervised Domain Adaptation by Backpropagation

Related

• Enhancing Neural Spoken Language Recognition: An Exploration with Multilingual Datasets
• AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition
• Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
• Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition
• Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognition