Character-Level Bangla Text-to-IPA Transcription Using Transformer Architecture with Sequence Alignment
This work addresses the need for automated IPA transcription in Bangla, a widely used language, to support applications like language learning and speech synthesis, but it is incremental as it applies existing transformer methods to a new domain.
The paper tackles the problem of converting Bangla text to International Phonetic Alphabet (IPA) transcription using a transformer-based sequence-to-sequence model, achieving a word error rate of 0.10582 and securing the top position in the DataVerse Challenge - ITVerse 2023.
The International Phonetic Alphabet (IPA) is indispensable in language learning and understanding, aiding users in accurate pronunciation and comprehension. Additionally, it plays a pivotal role in speech therapy, linguistic research, accurate transliteration, and the development of text-to-speech systems, making it an essential tool across diverse fields. Bangla being 7th as one of the widely used languages, gives rise to the need for IPA in its domain. Its IPA mapping is too diverse to be captured manually giving the need for Artificial Intelligence and Machine Learning in this field. In this study, we have utilized a transformer-based sequence-to-sequence model at the letter and symbol level to get the IPA of each Bangla word as the variation of IPA in association of different words is almost null. Our transformer model only consisted of 8.5 million parameters with only a single decoder and encoder layer. Additionally, to handle the punctuation marks and the occurrence of foreign languages in the text, we have utilized manual mapping as the model won't be able to learn to separate them from Bangla words while decreasing our required computational resources. Finally, maintaining the relative position of the sentence component IPAs and generation of the combined IPA has led us to achieve the top position with a word error rate of 0.10582 in the public ranking of DataVerse Challenge - ITVerse 2023 (https://www.kaggle.com/competitions/dataverse_2023/).