scholarly journals Auditory feature representation using convolutional restricted Boltzmann machine and Teager energy operator for speech recognition

2017 ◽  
Vol 141 (6) ◽  
pp. EL500-EL506 ◽  
Author(s):  
Hardik B. Sailor ◽  
Hemant A. Patil
Keyword(s):  
Speech Recognition ◽  
Energy Operator ◽  
Feature Representation ◽  
Restricted Boltzmann Machine ◽  
Boltzmann Machine ◽  
Teager Energy Operator ◽  
Auditory Feature ◽  
Teager Energy

scholarly journals Continuous Telugu Speech Recognition On T-LPC and DNN Techniques

2019 ◽  
Vol 8 (3) ◽  
pp. 4728-4731
Keyword(s):  
Neural Networks ◽  
Speech Recognition ◽  
Linear Prediction ◽  
Energy Operator ◽  
Teager Energy Operator ◽  
Regional Language ◽  
Signal Features ◽  
The World ◽  
Teager Energy ◽  
Prediction Filter

This paper deals with the basic application speech recognition. There are many languages in the world but one of the regional language is Telugu. Recognition of this language helps in many applications for 8 crores of people stay in AP and Telangana states. Recognition is done by recording the speech signals and database creation. Pre-processing is done by 2 stage DNN (seep neural networks) where denoising, framing is done. The preprocessed signal features are extracted using TLPC(teager energy operator linear prediction filter). The features extracted are classified using DNN which generates adequate results. The results are obtained for continuous speech of Telugu language

scholarly journals Isolated Telugu Speech Recognition On TDSCC And DNN Techniques

2019 ◽  
Vol 8 (11) ◽  
pp. 3419-3422
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Deep Neural Networks ◽  
Energy Operator ◽  
Independent Data ◽  
Teager Energy Operator ◽  
Classification Technique ◽  
Speaker Independent ◽  
Teager Energy ◽  
Feature Extraction Technique

Communication is the major path to convey the information. Speech is the best mode for conveying the information. Human to human information can be exchanged through some particular language. But the interaction between human and machine is the major challenge which deals with ASR (Automatic speech recognition). This research recognizes speaker independent data which gives good results by using TDSCC (Teager energy operator delta spectral cepstral coefficients) feature extraction technique and DNN (Deep Neural Networks) feature classification technique. This paper also uses CASA technique for pre-processing the speech signals. This research is done by creating the database for 10 most speak able isolated words in Telugu.

scholarly journals Operador de energía de teager para la detección de hipernasalidad en niños con labio y paladar hendido

TecnoLógicas ◽  
2011 ◽  
pp. 27 ◽  
Author(s):  
Juan R. Orozco-Arroyave ◽  
Jonny A. Uribe ◽  
Jesús F. Vargas-Bonilla
Keyword(s):  
Energy Operator ◽  
Teager Energy Operator ◽  
Teager Energy

El labio y/o paladar hendido (LPH) es una malformación, que tiene orígenes de tipo genético y ambiental. En Colombia, 6 de cada 10000 niños nacen con esta malformación, mientras en el resto del mundo la proporción se encuentra en 1 de cada 10000. El LPH trae consigo patologías en el habla tales como: hipernasalidad, hiponasalidad, golpe glótico, entre otras. De todas estas patologías, la hipernasalidad es la más recurrente en pacientes con LPH, apareciendo aproximadamente en el 90% de los casos. En este trabajo se hace un análisis, basado en resultados experimentales, del desempeño del Operador de Energía de Teager (TEO, por las siglas en inglés de Teager Energy Operator), para la detección de hipernasalidad en pacientes con LPH. Se analiza una versión generalizada del TEO con el fin de validar su capacidad discriminante en la detección de hipernasalidad, aplicándolo sobre una base de datos con registros de voz reales, de niños con LPH y niños control. Los resultados obtenidos comprueban que el TEO posee gran capacidad discriminante, y puede aportar información relevante en el proceso de detección de hipernasalidad.

Sign in / Sign up

Export Citation Format

Share Document