Enhancing Spoken Text With Punctuation Prediction Using N-Gram Language Model in Intelligent Technical Text Processing Software
Shweta Rani, Rhea Jain · Advances in systems analysis, software engineering, and high performance computing book series · 2024
Communication is a very important practice between two individuals, and for effective communication, the spoken text must be understood by others. Punctuation prediction is utmost essential in spoken text for bridging the language gaps. Various techniques have been proposed in the literature and are also explored. In this work, the authors developed software by studying n- gram model with probability to restore the punctuation in spoken text of technical lectures. In this chapter, the authors compared unigram, bigram, trigram, and quadgram method on varying size of datasets. Findings suggest that trigram model outperform the other for all three datasets and it was also noticed that increasing the gram size more do not have much impact on the performance of the software.