Gujarati speech emotion recognition datasets

KuralHub lists 1 speech emotion recognition dataset for Gujarati. Each entry below gives the emotion labels, size, recording setup, licence, where to get it and how to cite it.

Language family: Indo-European (Indo-Aryan)
ISO code: gu
Spoken mainly in: India
Datasets listed: 1
In benchmark: No

Datasets at a glance

Dataset	Type	Samples	Speakers	Recording	Access	Licence
Tank et al. (2020)	Audio	1296	9	Acted	On request

Tank et al. (2020)

Type: Audio
Emotion labels: Sadness, Surprise, Anger, Disgust, Fear, Happiness
Size: samples: 1296, speakers: 9
Speakers: 9
Recording: Acted
Access: On request
Licence: Not stated
File format: .wav
Paper: Paper Link
Contact: vishaltank.ec@charusat.ac.in

The dataset is a Gujarati emotional speech corpus designed for speech emotion recognition (SER). It contains speech samples categorized into six emotional states: sadness, surprise, anger, disgust, fear, and happiness. The dataset has been analyzed using pitch, energy, and MFCC features in MATLAB.

Citation

@article{article,
  author = {Tank, Vishal},
  year = {2020},
  month = {10},
  pages = {},
  title = {Creation of speech corpus for emotion analysis in Gujarati language and its evaluation by various speech parameters},
  volume = {10},
  journal = {International Journal of Electrical and Computer Engineering},
  doi = {10.11591/ijece.v10i5.pp4752-4758}
}

Source: datasets/Gujarati/Tank_et_al_2020.md · Suggest an edit

Know another Gujarati speech emotion dataset, or a newer version of one listed here? Suggest it or open a pull request.

This page is generated from datasets/Gujarati/ in the KuralHub repository. If you use a dataset, cite its authors. If KuralHub helped you find it, please also cite the KuralHub paper.