# EGGCodec: A Robust Neural Encodec Framework for EGG Reconstruction and F0 Extraction

arXiv: https://arxiv.org/abs/2508.08924 · HTML: https://mlsanity.com/paper/2508.08924/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [CREPE: A Convolutional Representation for Pitch Estimation](https://mlsanity.com/paper/1802.06182/) (2018)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning](https://mlsanity.com/paper/2401.17690/) (2024)
- [Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling](https://mlsanity.com/paper/2211.03038/) (2022)
- [Towards Improving Harmonic Sensitivity and Prediction Stability for Singing Melody Extraction](https://mlsanity.com/paper/2308.02723/) (2023)
- [Deep Learning-based F0 Synthesis for Speaker Anonymization](https://mlsanity.com/paper/2306.16860/) (2023)
- [Harmonic Detection from Noisy Speech with Auditory Frame Gain for Intelligibility Enhancement](https://mlsanity.com/paper/2401.11829/) (2024)

## Abstract (arXiv)

This letter introduces EGGCodec, a robust neural Encodec framework engineered for electroglottography (EGG) signal reconstruction and F0 extraction. We propose a multi-scale frequency-domain loss function to capture the nuanced relationship between original and reconstructed EGG signals, complemented by a time-domain correlation loss to improve generalization and accuracy. Unlike conventional Encodec models that extract F0 directly from features, EGGCodec leverages reconstructed EGG signals, which more closely correspond to F0. By removing the conventional GAN discriminator, we streamline EGGCodec's training process without compromising efficiency, incurring only negligible performance degradation. Trained on a widely used EGG-inclusive dataset, extensive evaluations demonstrate that EGGCodec outperforms state-of-the-art F0 extraction schemes, reducing mean absolute error (MAE) from 14.14 Hz to 13.69 Hz, and improving voicing decision error (VDE) by 38.2%. Moreover, extensive ablation experiments validate the contribution of each component of EGGCodec.