arXiv:2606. 10972v1 Announce Type: cross Abstract: This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning.
This study aims to explore the performance of the VAR model in comparison with mel-frequency cepstral coefficient (MFCC) matrices and log-mel spectrograms using deep learning. In pulmonary sound classification, spectrogram-based representations suffer from inconsistent temporal dimensions due to varying respiratory cycle durations.
arXiv:2610.15702v1 Announce Type: cross Abstract: Respiratory auscultation provides a low-cost means of assessing pulmonary function, yet transient crackles and sustained wheezes can be difficult to...
The study compares classical and deep learning classifiers for a five‑class respiratory‑sound dataset of 1,211 clips. An SVM using 30 summary features (MFCC, ZCR, RMS) achieves macro recall of 0.78, while a 1.13M‑parameter convolutional‑recurrent network reaches 0.75–0.77; no clear advantage is found between model families. The largest performance gain comes from standardizing the SVM’s features, which boosts macro recall by 27 points, far exceeding any architectural difference.
WIPSNet is a 3D ResNet that processes stacked continuous wavelet transform scalograms of overnight impedance pneumography (IP) signals to detect paediatric wheeze. In a study of 15 patients (60 nights, 281 hours), it achieved an AUC of 0.783 ± 0.026, outperforming the traditional Expiratory Variability Index, a state‑space model, and two modern sleep‑staging architectures. The model’s best performance occurs with a 32‑minute temporal context, highlighting the importance of multi‑scale temporal aggregation for nocturnal respiratory dynamics.
The study evaluates a pipeline for detecting dysarthria during awake craniotomy using the DATABRASE corpus. It combines speaker diarization, a multi‑view representation of handcrafted acoustic features and wav2vec 2.0 embeddings, speaker‑conditional normalization, feature selection, and a cascaded classifier. Results show that the speech representation has a larger impact on cross‑speaker performance than classifier choice, with self‑supervised embeddings improving AUC by 18.2%–26.1% and additional gains from diarization‑conditioned extraction and the classifier cascade.
DualStabSleepNet (DSSNet) is a dual-domain diffusion stabilization network designed to improve the robustness of automatic sleep staging across heterogeneous recording conditions. It employs a continuous-scale diffusion-based module to suppress noise while preserving physiological signals, then transforms stabilized signals into time-frequency representations for a Vision Transformer backbone. A teacher‑student guided diffusion feature stabilization further reduces feature drift, achieving state‑of‑the‑art accuracy on four public PSG datasets and demonstrating strong performance under cross‑dataset distribution shifts.
BreathGRU is a semi‑supervised Bidirectional Gated Recurrent Unit framework designed to segment speech and breath events in respiratory audio. It combines acoustic feature extraction, bidirectional recurrent modeling, pseudo‑label refinement, and duration‑constrained Segmental Viterbi decoding to produce accurate speech‑breath segmentation. In evaluations against existing methods, BreathGRU achieved the highest breath event recall, lowest onset‑localisation error, and highest Mean Match Intersection over Union, outperforming large pretrained VAD models such as Silero.
arXiv:2606. 08247v1 Announce Type: cross Abstract: Acute asthma risk assessment requires rapid interpretation of respiratory sounds, oxygenation, airflow limitation, speech ability, work of breathing, mental status, and response to reliever therapy.
arXiv:2606. 11922v1 Announce Type: cross Abstract: Recent respiratory sound classification (RSC) studies largely rely on CLS-token driven self-attention architectures such as the Audio Spectrogram Transformer (AST).
arXiv:2512. 14461v2 Announce Type: replace Abstract: Sleep is essential for health, yet studying its dynamics requires manual sleep staging, a labor-intensive step in research and clinical care.
The study presents deep learning‑based segmentation of laryngeal structures in high‑speed videoendoscopy (HSV) data, including connected speech. Using U‑Net models, the authors trained networks to detect aryepiglottic folds, arytenoid cartilages, vocal folds, epiglottis, and glottal area from HSV recordings of both sustained vowel phonation and connected speech in normal and disordered voices. After applying noise removal and histogram equalization, the networks achieved overall accuracies above 95%, demonstrating reliable automated analysis of laryngeal dynamics.