Real Time Captioning and Notes Making of Online Classes
5th IFIP TC 12 International Conference on Computational Intelligence in Data Science, ICCIDS 2022
; 654 IFIP:207-220, 2022.
Article
Dans Anglais
| Scopus | ID: covidwho-2094429
ABSTRACT
Due to the COVID-19 pandemic, all activities have turned online. The people who are hard of hearing are facing high difficulty to continue their education. So, the presented system supports them in attending the online classes by providing the real time captions. Additionally, it provides summarized notes for all the students so that they can refer to them before the next class. Google Speech to Text API is used to convert the speech to text, for providing real time captions. Three text summarization models were explored, namely BART, Seq2Seq model and the TextRank algorithm. The BART and the Seq2Seq models require a labelled dataset for training, whereas the TextRank algorithm is an unsupervised learning algorithm. For BART, the dataset is built using semi supervised methods. We evaluated all these models with rouge score evaluation metrics, among these BART proves to be best for our dataset with the following scores of 0.47, 0.30, 0.48 for rouge-1, rouge-2 and rouge-l respectively. © 2022, IFIP International Federation for Information Processing.
Texte intégral:
Disponible
Collection:
Bases de données des oragnisations internationales
Base de données:
Scopus
langue:
Anglais
Revue:
5th IFIP TC 12 International Conference on Computational Intelligence in Data Science, ICCIDS 2022
Année:
2022
Type de document:
Article
Documents relatifs à ce sujet
MEDLINE
...
LILACS
LIS