5 citations · 12 across the 6 of their papers we have counts for
7 papers
Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages
Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu +3
This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proc…
DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages
Paul Azunre, Naafi Ibrahim, Joel Budu +1
We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech enc…
GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages
Lawrence Adu Gyamfi, Paul Azunre, Stephen Edward Moore +4
Low resource languages present unique challenges for natural language processing due to the limited availability of digitized and well structured linguistic data. To address this g…
Data Subsampling for Bayesian Neural Networks
Eiji Kawasaki, Markus Holzmann, Lawrence Adu-Gyamfi
Markov Chain Monte Carlo (MCMC) algorithms do not scale well for large datasets leading to difficulties in Neural Network posterior sampling. In this paper, we propose Penalty Baye…
English-Twi Parallel Corpus for Machine Translation
Paul Azunre, Salomey Osei, Salomey Addo +24
We present a parallel machine translation training corpus for English and Akuapem Twi of 25,421 sentence pairs. We used a transformer-based translator to generate initial translati…
NLP for Ghanaian Languages
Paul Azunre, Salomey Osei, Salomey Addo +24
NLP Ghana is an open-source non-profit organization aiming to advance the development and adoption of state-of-the-art NLP techniques and digital language tools to Ghanaian languag…
Contextual Text Embeddings for Twi
Paul Azunre, Salomey Osei, Salomey Addo +24
Transformer-based language models have been changing the modern Natural Language Processing (NLP) landscape for high-resource languages such as English, Chinese, Russian, etc. Howe…