# Chirp Localization via Fine-Tuned Transformer Model: A Proof-of-Concept Study

arXiv: https://arxiv.org/abs/2503.22713 · HTML: https://mlsanity.com/paper/2503.22713/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 34 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 30 of 33)

- [Taming Visually Guided Sound Generation](https://mlsanity.com/paper/2110.08791/) (2021)
- [Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM](https://mlsanity.com/paper/2305.15255/) (2023)
- [A-JEPA: Joint-Embedding Predictive Architecture Can Listen](https://mlsanity.com/paper/2311.15830/) (2023)
- [Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis](https://mlsanity.com/paper/2012.07267/) (2020)
- [StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing](https://mlsanity.com/paper/2402.12636/) (2024)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer](https://mlsanity.com/paper/2410.05151/) (2024)
- [MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations](https://mlsanity.com/paper/2503.01019/) (2025)
- [Vision Language Models Are Few-Shot Audio Spectrogram Classifiers](https://mlsanity.com/paper/2411.12058/) (2024)
- [Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations](https://mlsanity.com/paper/2503.03062/) (2025)
- [Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Models](https://mlsanity.com/paper/2407.01777/) (2024)
- [SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG](https://mlsanity.com/paper/2501.10402/) (2025)
- [Feature-informed Embedding Space Regularization For Audio Classification](https://mlsanity.com/paper/2206.04850/) (2022)
- [Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning](https://mlsanity.com/paper/2405.08679/) (2024)
- [SF-Speech: Straightened Flow for Zero-Shot Voice Clone](https://mlsanity.com/paper/2410.12399/) (2024)
- [RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems](https://mlsanity.com/paper/2503.04252/) (2025)
- [ConfIC-RCA: Statistically Grounded Efficient Estimation of Segmentation Quality](https://mlsanity.com/paper/2503.04522/) (2025)
- [Speech Emotion Recognition via an Attentive Time-Frequency Neural Network](https://mlsanity.com/paper/2210.12430/) (2022)
- [PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders](https://mlsanity.com/paper/2404.02702/) (2024)
- [Blind Acoustic Parameter Estimation Through Task-Agnostic Embeddings Using Latent Approximations](https://mlsanity.com/paper/2407.19989/) (2024)
- [Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching](https://mlsanity.com/paper/2411.02026/) (2024)
- [Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning](https://mlsanity.com/paper/2501.10052/) (2025)
- [Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings](https://mlsanity.com/paper/2502.07025/) (2025)
- [NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing](https://mlsanity.com/paper/2502.12002/) (2025)
- [BrainTalker: Low-Resource Brain-to-Speech Synthesis with Transfer Learning using Wav2Vec 2.0](https://mlsanity.com/paper/2312.13600/) (2023)
- [DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model](https://mlsanity.com/paper/2502.18952/) (2025)
- [Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention](https://mlsanity.com/paper/2503.01284/) (2025)
- [HiGP: A high-performance Python package for Gaussian Process](https://mlsanity.com/paper/2503.02259/) (2025)
- [A Generative Approach to High Fidelity 3D Reconstruction from Text Data](https://mlsanity.com/paper/2503.03664/) (2025)
- [EIHW-MTG: Second DiCOVA Challenge System Report](https://mlsanity.com/paper/2110.09239/) (2021)

## Built on by (most cited first, 1 of 1)

- [Classifying Clinical Outcome of Epilepsy Patients with Ictal Chirp Embeddings](https://mlsanity.com/paper/2508.13476/) (2025)

## Abstract (arXiv)

Spectrograms are pivotal in time-frequency signal analysis, widely used in audio processing and computational neuroscience. Chirp-like patterns in electroencephalogram (EEG) spectrograms (marked by linear or exponential frequency sweep) are key biomarkers for seizure dynamics, but automated tools for their detection, localization, and feature extraction are lacking. This study bridges this gap by fine-tuning a Vision Transformer (ViT) model on synthetic spectrograms, augmented with Low-Rank Adaptation (LoRA) to boost adaptability. We generated 100000 synthetic spectrograms with chirp parameters, creating the first large-scale benchmark for chirp localization. These spectrograms mimic neural chirps using linear or exponential frequency sweep, Gaussian noise, and smoothing. A ViT model, adapted for regression, predicted chirp parameters. LoRA fine-tuned the attention layers, enabling efficient updates to the pre-trained backbone. Training used MSE loss and the AdamW optimizer, with a learning rate scheduler and early stopping to curb overfitting. Only three features were targeted: Chirp Start Time (Onset Time), Chirp Start Frequency (Onset Frequency), and Chirp End Frequency (Offset Frequency). Performance was evaluated via Pearson correlation between predicted and actual labels. Results showed strong alignment: 0.9841 correlation for chirp start time, with stable inference times (137 to 140s) and minimal bias in error distributions. This approach offers a tool for chirp analysis in EEG time-frequency representation, filling a critical methodological void.