An empirical comparison of deep CNN architectures for heart sound classification from phonocardiogram signals. [PDF]
Front PhysiolAl Tawil A, Bin Sheeha B, Aburub A.
europepmc +1 more source
Spoken Language Identification using Mel-Spectrogram
In this study, a model was developed to automatically identify five of the most widely spoken languages (English, French, German, Spanish, and Turkish) based on speech signals. The features of each audio recording were extracted using the Mel-spectrogram method and converted into grayscale images, which were then used to construct the dataset.
openaire +1 more source
Hybrid CNN-embedding fusion with MFCC-SVM for speech emotion recognition: Random vs actor-wise evaluation on CREMA-D. [PDF]
PLoS OneKumari P +7 more
europepmc +1 more source
Implementing Mel-Spectrogram Analysis for Emotion Recognition in Speech
INTERNATIONAL JOURNAL OF RESEARCH IN SCIENCE AND TECHNOLOGY, 2023 openaire +1 more source
Speech-based concussion detection in athletes using Mel-spectrograms and convolutional neural networks. [PDF]
Front NeurolRubaiat R, Poellabauer C.
europepmc +1 more source
Spatial-Temporal Relation Enhancement for Speech Emotion Recognition from Acoustic Signals Using Fibonacci Encoding with Diverse Feature Fusion. [PDF]
Sensors (Basel)Huang S +9 more
europepmc +1 more source
Overcoming Data Scarcity: Few-Shot Pig Vocalization Recognition via Domain Expansion, Knowledge Transfer, and Feature Alignment. [PDF]
Animals (Basel)Li G, Liu W.
europepmc +1 more source
Demographic Confounding in Voice-Based Parkinson Disease Screening: Methodological Analysis of the Bridge2AI Voice Dataset. [PDF]
J Med Internet ResShukla S +3 more
europepmc +1 more source
Explainable Multi-Modal Deep Learning for Recording-Level Classification of Respiratory Audio Signals Under Internal and Domain-Shift Evaluation. [PDF]
Life (Basel)Saky SMAI +8 more
europepmc +1 more source