Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

AkaCE: A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues for the Akan Language

Domaine:

natural language processing

Type de record:

dataset
Créateur:
SasWu,GonChe

The Akan Cinematic Emotions (AkaCE) dataset is the first multimodal speech emotion recognition (SER) dataset for any African language, specifically developed for Akan, a widely spoken West African language. It includes: 385 dialogues from Akan-language movies; 6,162 utterances from 308 speakers (balanced by gender); rich multimodal data: audio, visual, and text; seven emotion labels (Sadness, Fear, Anger, Surprise, Disgust, Happy, Neutral); word-level prosodic prominence annotations — making it the first prosodically annotated dataset for any African language.

Visit

github.com

Connected records

paper

Tasks

speech processingautomatic speech recognitionemotion identification

Languages

Akan

Tags

emotion recognitionspeech emotion recognitionmultimodalprosodymovie dialogues

Licenses

Non-commercial research use only, see LICENSE.txt

Similaires

Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues

Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues

In this paper, we introduce the Akan Conversation Emotion (ACE) dataset, the first multimodal emotion dialogue dataset for an African language, addressing the significant lack of resources for low-resource languages in emotion recognition research. ACE, developed f