Optimising a Language Recognition System Through Phoneme-Based Vector Representation

Optimising a Language Recognition System Through Phoneme-Based Vector Representation

This article analyzes vector representation of phonemes as an alternative to improve a language identification system (LID). CBOW (Continuous Bag-of-Words) and Skip-gram architectures proposed by Mikolov are studied. These models allow predicting words within a context by generating n-dimensional ve...

Full description

Bibliographic Details
Main Authors: Francisco Charro, Marco Herrera, Nataly Pozo, Andrés Rosales
Format: Article
Language:English
Published: Escuela Politécnica Nacional (EPN) 2017-11-01
Series:Latin-American Journal of Computing
Subjects:
vector representation
language recognition
skip-gram
n-grams
embeddings.
Online Access:https://lajc.epn.edu.ec/index.php/LAJC/article/view/130

Internet

https://lajc.epn.edu.ec/index.php/LAJC/article/view/130

Similar Items