23 November 2024 in ACM Transactions on Asian and Low-Resource Language Information Processing
Many sub-Saharan African languages are categorized as tone languages, and for the most part, they are classified as low-resource languages due to the limited resources and tools available to process these languages. Identifying the tone associated with a syllable is therefore a key challenge for speech recognition in these languages. We propose models that automate the recognition of tones in continuous speech that can easily be incorporated into a speech recognition pipeline for these languages. We have investigated different neural architectures as well as several feature extraction algorithms in speech (FBs (Filter Banks), LEAF (Learnable Frontend), CS (Cestrogram), MFCC (Mel-Frequency Cepstral Coefficients)). In the context of low-resource languages, we also evaluated W2V (Wav2vec 2.0) models for this task. In this work, we use a public speech recognition dataset on Yoruba. As for the results, using the combination of features obtained from CS and FBs, we obtain a minimum TER (Tone Error Rate) of 19.54%, whereas for the evaluations of the models using W2V, we have a TER of 17.72%, demonstrating that the use of W2V provides better performance than the models used in the literature for tone identification on low-resource languages.
31 March 2009 in Mathematical Social Sciences
31 January 2008 in Acta Applicandae Mathematicae
29 September 2020 in Revue Africaine de La Recherche En Informatique Et Mathématiques Appliquées
MMMichael Franklin Mbouopda
Michael Franklin Mbouopda
Named Entity Recognition (NER) is a fundamental task in many NLP applications that seek to identify and classify expressions such as people, location, and organization names. Many NER systems have been developed, but the annotated data needed for good performances are not available for low-resource languages, such as Cameroonian languages. In this paper we exploit the low frequency of named entities in text to define a new suitable cross-lingual distributional representation for named entity recognition. We build the first Ewondo (a Bantu low-resource language of Cameroon) named entities recognizer by projecting named entity tags from English using our word representation. In terms of Recall, Precision and F-score, the obtained results show the effectiveness of the proposed distributional representation of words La reconnaissance des entités nommées (REN) est une tâche fondamentale du TALN dont le but est d'identifier les expressions telles que les noms de personnes, de lieux et d'organisations dans un texte. Il existe de nos jours plusieurs systèmes de REN, cependant les données nécessaires pour les utiliser dans le traitement des langues peu dotées telles que les langues camerounaises ne sont pas disponibles. Nous exploitons le fait que les entités nommées apparaissent rarement dans les textes pour définir une nouvelle représentation distributionnelle interlingue des mots, qui soit adaptée à la REN. En utilisant notre représentation, nous projectons les entités nommées de l'anglais vers l'ewondo (une langue bantou du Cameroun); nous obtenons donc le tout premier modèle de reconnaissance des entités nommées en langue ewondo. Les résultats en terme de précision, rappel et f-mesure montrent l'efficacité de notre représentation
27 November 2023 in Data in Brief
Prosody is a key area of linguistics that explores tonal and rhythmic variations in speech. In tonal languages such as Yemba, prosody plays a crucial role in distinguishing between words with different meanings or different grammatical forms. However, despite the large number of native speakers of this language in Cameroon, there are few resources for the speech recognition and synthesis. In this article, we present YembaTones, a syllabic and tonal annotated dataset, created from a dictionary we designed of 344 Yemba/French words coming from the most common phrases of the language, grouped according to their spellings that only differ by the tone. The dataset was originally designed for training and evaluating tone detection models for tonal and low resource languages. The recordings of the pronunciation of these words were made with 11 native speakers of Yemba, mainly specialists in linguistics with a good command of the sounds of the language. The recordings were made with a dictaphone in different places such as the homes of the speakers, the campuses and their workplaces. Then they have been cleaned and segmented into individual audio files corresponding to the pronunciations of iso lated words, using the software Audacity. After cleaning and segmentation, we selected 3420 good quality audio files for annotation. Annotations were made at the syllabic and tonal level using Praat software. YembaTones is a valuable resource not only for the training and evaluation of automatic tone detection models but also for automatic speech recognition, speech synthesis of tonal and poorly endowed languages, as well as for the study of prosody and Yemba phonetics, research in speech acoustics and phonetic linguistics. (c) 2023 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )