Actuator prototype system by voice commands using free software


  • Jaime Andrango Universidad de las Fuerzas Armadas
  • Estevan Gómez Universidad Tecnológica Equinoccial



voice recognition, voice commands, spectral differences, python, free software applications


This prototype system is a software application that through the use of techniques of digital signal processing, extracts information from the user's speech, which is then used to manage the on/off actuator on a peripheral computer when vowels are pronounced. The method applies spectral differences. The application uses the parallel port as actuator, with the information recorded in the memory address 378H. This prototype was developed using free software tools for its versatility and dynamism, and to allow other researchers to base on it for further studies.



Download data is not yet available.


A. Larcher, K.-A. L. (2013). “Phoneticallyconstrained PLDA modeling for text-dependent speaker verification with multiple short utterances”. IEEE Internationall Conference on Acoustics, Speech, and Signal ,Processing (ICASSP).
Audacity. (29 de 04 de 2016). Audacity Español. Obtenido de Audacity Español:
Bernal, J. (2000). Reconocimiento de Voz y Fonética Acústica. Madrid: Ra-Ma.
Chen, Y. L.-M. (2015). “Locallyconnected d and convolutional neural networks for smalL footprint speaker recognition,”. Interspeech.
García, C., & Tapia, D. (2000). Estudio de la Frecuencia Fundamental de la Voz y de sus Efectos en el. Proyecto de Fin de Carrera E.T.S.I. Madrid, España: U. Politécnica de Madrid.
Grayson, J. (2000). Phyton and Tkinter Programming‖, . Manning Publications Co.
H. Aronowitz, R. H. (2011). “New developments in voice biometrics for user. n Interspeech, Florence, 17-20.
Hans, P. (2011). A Primer on Scientific Programming with Python. New York: Springer.
Phyton. (29 de 04 de 2016). Idle Phyton. Obtenido de Idle Phyton:
Phyton. (29 de 04 de 2016). Python GUI Programming (Tkinter). Obtenido de Python GUI Programming (Tkinter):
Poor, H. (1985). An Introduction to Signal Detection and Estimation. New York: Springer- Verlag.
Thomas, T., Pecham, J., & Frangoulis, E. (1989). A Determination of the Sensitivity of Speech Recognisers to Speaker Variability. Proceedings of ICASSP, (págs. 544-547). Glasgow.
Thomas, T., Pecham, J., Frangoulis, E., & Cove, J. (14989). A The Sensitivity of Speech Recognisers to Speaker Variability and Speaker Variation. Proc of Eurospeech, (págs. 408-411). Paris.



How to Cite

Andrango, J., & Gómez, E. (2016). Actuator prototype system by voice commands using free software. Enfoque UTE, 7(2), pp. 41 - 54.