Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · 2018

Time Window Analysis for Automatic Speech Emotion Recognition

Boris Puterka, Juraj Kačur

Cited by 11Abstract and details only

Abstract

In this paper we present time analysis results of speech emotion recognition using convolutional neural network architecture and spectrograms as a speech features. Analyses were performed on model with two convolutional layers followed by pooling layer, and one fully-connected layer followed by dropout and softmax layer on the output. On this model we analyzed time characteristics of speech signal represented by spectrograms. The aim of our work was to find relation between duration of speech signal and the recognition rate of seven basic emotions. It was discovered that speech length is important and naturally the accuracy is growing with the length of analyzed window, however over approximately 1.2 seconds the growth becomes rather mild.

Cite this paper

APA 7

Puterka, B., & Kačur, J. (2018). Time Window Analysis for Automatic Speech Emotion Recognition. https://doi.org/10.23919/elmar.2018.8534630

MLA 9

Puterka, Boris, and Juraj Kačur. “Time Window Analysis for Automatic Speech Emotion Recognition.” 2018, pp. 143–46, https://doi.org/10.23919/elmar.2018.8534630.

Chicago

Puterka, Boris, and Juraj Kačur. 2018. “Time Window Analysis for Automatic Speech Emotion Recognition.” https://doi.org/10.23919/elmar.2018.8534630.

Harvard

Puterka, B. and Kačur, J. (2018) ‘Time Window Analysis for Automatic Speech Emotion Recognition’. Available at: https://doi.org/10.23919/elmar.2018.8534630.

BibTeX
@article{puterka2018time,
  title = {{Time Window Analysis for Automatic Speech Emotion Recognition}},
  author = {Puterka, Boris and Kačur, Juraj},
  pages = {143--146},
  year = {2018},
  doi = {10.23919/elmar.2018.8534630}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers