Results 81 to 90 of about 3,813 (182)

Computing nasalance with MFCCs and Convolutional Neural Networks

PLOS ONE
Nasalance is a valuable clinical biomarker for hypernasality. It is computed as the ratio of acoustic energy emitted through the nose to the total energy emitted through the mouth and nose (eNasalance). A new approach is proposed to compute nasalance using Convolutional Neural Networks (CNNs) trained with Mel-Frequency Cepstrum Coefficients ...
Andrés Lozano, Enrique Nava, María Dolores García Méndez, Ignacio Moreno-Torres   +3 more
openaire   +3 more sources

Hyperparameter Optimization of CNN Based Open Set Speaker Verification Using MFCC and Speaker Embedding for Voice Biometric Security

Journal of Applied Informatics and Computing
The development of voice based biometric security systems has increased the demand for authentication methods capable of operating accurately and securely in open set speaker verification scenarios.
Mirza Ardiana, Mat Syai’in, Alief Nur Aisyi Maulidhia, Aulia Rahma Annisa, Yudi Andika, Sholahuddin Muhammad Irsyad, Fauzan Izzul Haq   +6 more
doaj   +1 more source

MEL frequency cepstral coefficients (MFCC) of original speakers and their imitators

Archives of Acoustics, 2014
The results of intra- and interspeaker distances between MFCC vectors obtained from speech samples of eight well-known Polish personalities and their imitations performed by cabaret entertainers are presented and discussed.
W. Majewski
doaj  

Tumor microenvironment responsive nano-immunoregulator for precision cancer photodynamic immunotherapy. [PDF]

Mater Today Bio
Chang X, Yu M, Wei P, Cheng J, Wu Y.
europepmc   +1 more source

A lightweight hybrid attention network with multi-scale feature integration for intelligent recognition of underwater acoustic targets. [PDF]

Sci Rep
Mahmud NA, Zhang T, Iqbal Y, Sumona FB, Iqbal A, Geng Y, Khan W, Zneid BA, Zaitsev I.   +8 more
europepmc   +1 more source

Machine Learning Approaches to Early Detection of Parkinson's Disease Using Speech Analysis Technique. [PDF]

Neurol Int
Hossain MA, Traini E, Amenta F.
europepmc   +1 more source

Advancing insect monitoring: analysis of mel-frequency cepstral coefficients from optical signals for body orientation estimation. [PDF]

Appl Phys B
Saha T, Thomas BP.
europepmc   +1 more source

Advancing cardiovascular screening: deep learning-based heart-sound classification using SMOTE and temporal modeling. [PDF]

Sci Rep
Ameen A, Eldesouky Fattoh I, Abd El-Hafeez T, Ahmed K.   +3 more
europepmc   +1 more source

Speech Recognition with an fMRISNN Constrained by Human Functional Brain Networks: A Study of Enhanced MFCC-Driven Sparse Spike Encoding. [PDF]

Biomimetics (Basel)
Guo L, Ma N, Wang Z, Liu R.
europepmc   +1 more source

A dual-branch deep learning framework for emotion recognition from EEG signals. [PDF]

Sci Rep
Saha D, Ali A, Gulvanskii V, Kaplun D, Sarkar R.   +4 more
europepmc   +1 more source