LMU-Based Sequential Learning and Posterior Ensemble Fusion for Cross-Domain Infant Cry Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914563581018112 |
|---|---|
| author | Jazaeri, Niloofar Dajani, Hilmi R. Janeczek, Marco Bouchard, Martin |
| author_facet | Jazaeri, Niloofar Dajani, Hilmi R. Janeczek, Marco Bouchard, Martin |
| contents | Decoding infant cry causes remains challenging for healthcare monitoring due to short nonstationary signals, limited annotations, and strong domain shifts across infants and datasets. We propose a compact acoustic framework that fuses mel-frequency cepstral coefficients (MFCCs), short-time Fourier transform (STFT) features, and fundamental-frequency (F0) contours within a multi-branch convolutional neural network (CNN) encoder, and models temporal dynamics using an enhanced Legendre Memory Unit (LMU). Compared to LSTMs, the LMU backbone provides stable sequence modeling with substantially fewer recurrent parameters, supporting efficient deployment. To improve cross-dataset generalization, we introduce calibrated posterior ensemble fusion with entropy-gated weighting to preserve domain-specific expertise while mitigating dataset bias. Experiments on Baby2020 and Baby Crying demonstrate improved macro-F1 under cross-domain evaluation, along with leakage aware splits and real-time feasibility for on-device monitoring. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02245 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LMU-Based Sequential Learning and Posterior Ensemble Fusion for Cross-Domain Infant Cry Classification Jazaeri, Niloofar Dajani, Hilmi R. Janeczek, Marco Bouchard, Martin Audio and Speech Processing Machine Learning Sound Decoding infant cry causes remains challenging for healthcare monitoring due to short nonstationary signals, limited annotations, and strong domain shifts across infants and datasets. We propose a compact acoustic framework that fuses mel-frequency cepstral coefficients (MFCCs), short-time Fourier transform (STFT) features, and fundamental-frequency (F0) contours within a multi-branch convolutional neural network (CNN) encoder, and models temporal dynamics using an enhanced Legendre Memory Unit (LMU). Compared to LSTMs, the LMU backbone provides stable sequence modeling with substantially fewer recurrent parameters, supporting efficient deployment. To improve cross-dataset generalization, we introduce calibrated posterior ensemble fusion with entropy-gated weighting to preserve domain-specific expertise while mitigating dataset bias. Experiments on Baby2020 and Baby Crying demonstrate improved macro-F1 under cross-domain evaluation, along with leakage aware splits and real-time feasibility for on-device monitoring. |
| title | LMU-Based Sequential Learning and Posterior Ensemble Fusion for Cross-Domain Infant Cry Classification |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2603.02245 |