Javanese speech emotion recognition datasets

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

Language family: Austronesian (Malayo-Polynesian)
ISO code: jv
Spoken mainly in: Indonesia
Datasets listed: 1
In benchmark: No

Datasets at a glance

Dataset	Type	Samples	Speakers	Recording	Access	Licence
Java-SED	Audio	1680	20	Acted	On request

Java-SED

Type: Audio
Emotion labels: Neutral, Sad, Happy, Surprised, Fear and Anger
Size: samples - 1680, speakers -20
Speakers: 20
Recording: Acted
Access: On request
Licence: Not stated
File format: .wav
Website: Dataset Homepage
Paper: Paper Link
Download: Download
Contact: rg.beais.uny@gmail.com, fatchul@uny.ac.id

The Javanese Emotional Speech Database is the first publicly available dataset for recognizing emotions in Javanese speech. Created using recordings from ten trained actors (five men, five women) aged 20–30, it includes six emotions: happy, sad, fear, angry, neutral, and surprised. The recordings were validated by 30 Javanese-speaking verifiers and a machine learning system, confirming its reliability for emotion recognition. The dataset is open-source and accessible to the research community at this link.

Citation

@article{article,
  author = {Arifin, Fatchul and Priambodo, Ardy and Nasuha, Aris and Winursito, Anggun and Gunawan, Teddy},
  year = {2022},
  month = {09},
  pages = {},
  title = {Development of Javanese Speech Emotion Database (Java-SED)},
  volume = {10},
  journal = {Indonesian Journal of Electrical Engineering and Informatics (IJEEI)},
  doi = {10.52549/ijeei.v10i3.3888}
}

Source: datasets/Javanese/Java-SED.md · Suggest an edit

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

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