scholarly journals Novel energy separation based instantaneous frequency features for spoof speech detection

2017 ◽  
Author(s):  
Madhu R. Kamble ◽  
Hemant A. Patil
Keyword(s):  
Instantaneous Frequency ◽  
Energy Separation ◽  
Speech Detection ◽  
Frequency Features

Instantaneous Frequency Features for Noise Robust Speech Recognition

2019 ◽  
Author(s):  
Shekhar Nayak ◽  
Dhar B. Shashank ◽  
Saurabhchand Bhati ◽  
Koilakuntla Bramhendra ◽  
K. Sri Rama Murty
Keyword(s):  
Speech Recognition ◽  
Instantaneous Frequency ◽  
Robust Speech Recognition ◽  
Noise Robust Speech Recognition ◽  
Noise Robust ◽  
Frequency Features

Long-term high frequency features for synthetic speech detection

2020 ◽  
Vol 97 ◽  
pp. 102622 ◽  
Author(s):  
Jichen Yang ◽  
Rohan Kumar Das
Keyword(s):  
High Frequency ◽  
Synthetic Speech ◽  
Speech Detection ◽  
Frequency Features

scholarly journals Deep Recurrent Learning for Heart Sounds Segmentation based on Instantaneous Frequency Features

Elektron ◽  
2020 ◽  
Vol 4 (2) ◽  
pp. 52-57
Author(s):  
Alvaro Joaquin Gaona ◽  
Pedro David Arini
Keyword(s):  
Instantaneous Frequency ◽  
Short Term Memory ◽  
Heart Sounds ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Para Determinar ◽  
Frequency Features

En este trabajo se presenta un conjunto de técnicas bien conocidas definiendo un método automático para determinar los sonidos fundamentales en un fonocardiograma (PCG). Mostraremos una red neuronal recurrente capaz de segmentar segmentar un fonocardiograma en sus principales componentes, y una forma muy específica de extraer frecuencias instantáneas que jugarán un importante rol en el entrenamiento y validación del modelo propuesto. Más específicamente, el método propuesto involucra una red neuronal Long Short-Term Memory (LSTM) acompañada de la Transformada Sincronizada de Fourier (FSST) usada para extraer atributos en tiempo-frecuencia en un PCG. El presente enfoque fue evaluado con señales de fonocardiogramas mayores a 5 segundos y menores a 35 segundos de duración extraı́dos de bases de datos públicas. Se demostró, que con una arquitectura relativamente pequeña, un conjunto de datos acotado y una buena elección de las características, este método alcanza una eficacia cercana a la del estado del arte, con una sensitividad promedio de 89.5%, una precisión promedio de 89.3% y una exactitud promedio de 91.3%.

scholarly journals Comparison of Frequency Features of Pulse Echoes from Different Reflectors

2011 ◽  
Vol 2011 ◽  
pp. 1-8 ◽  
Author(s):  
Anatoly B. Rinkevich ◽  
Olga V. Nemytova ◽  
Dmitry V. Perov
Keyword(s):  
Instantaneous Frequency ◽  
Piezoelectric Transducer ◽  
Wavelet Transformation ◽  
Noise Immunity ◽  
Elastic Media ◽  
Frequency Determination ◽  
Pulse Echo ◽  
Frequency Features

The analysis of interaction of ultrasonic pulses with different reflectors which are located in elastic media is carried out. A parameter which allows estimating the form of reflector is instantaneous frequency of pulse-echo. This parameter is an unsteady pulse echo characteristic. Instantaneous frequency determination algorithm is to use wavelet transformation which has increased noise immunity. It is shown that the instantaneous frequency value for a pulse echo is often shifted from a rated frequency of piezoelectric transducer. Difference between the frequencies extensively depends on the reflector form.

Sign in / Sign up

Export Citation Format

Share Document