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.

Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings

Type de record:

dataset
Créateur:
Lev
Éditeur:
Lev
Éditeur:
TIB
Hôte:avatar
A dataset for the Zero Resource Speech Challenge 2015.

Tasks

embeddingsspeech processing

Tags

natural language processingspeech recognitionzero-resource speech

Similaires

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddingsMultilingual acoustic word embeddings for zero-resource languagesTowards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and SwahiliIsomorphic Cross-lingual Embeddings for Low-Resource LanguagesLearning Stress in Arabic Low-Resource SettingsThermal Cautery for Low Resource Settings

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings

We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWE

Multilingual acoustic word embeddings for zero-resource languages

This research addresses the challenge of developing speech applications for zero-resource languages

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili

We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to b

Isomorphic Cross-lingual Embeddings for Low-Resource Languages

Cross-Lingual Word Embeddings (CLWEs) are a key component to transfer linguistic information learnt

Learning Stress in Arabic Low-Resource Settings

We predict lexical stress in Arabic varieties from syllable structure, modeling stress assignment as

Thermal Cautery for Low Resource Settings

International Heat, a team of five graduate students, spent the past four months designing a thermal