Omer Beg

Saad Naeem, Omer Beg

Phoneme recognition is a largely unsolved problem in NLP, especially for low-resource languages like Urdu. The systems that try to extract the phonemes from audio speech require hand-labeled phonetic transcriptions. This requires expert linguists to annotate speech data with its relevant phonetic representation which is both an expensive and a tedious task. In this paper, we propose STRATA, a framework for supervised phoneme recognition that overcomes the data scarcity issue for low resource languages using a seq2seq neural architecture integrated with transfer learning, attention mechanism, and data augmentation. STRATA employs transfer learning to reduce the network loss in half. It uses attention mechanism for word boundaries and frame alignment detection which further reduces the network loss by 4% and is able to identify the word boundaries with 92.2% accuracy. STRATA uses various data augmentation techniques to further reduce the loss by 1.5% and is more robust towards new signals both in terms of generalization and accuracy. STRATA is able to achieve a Phoneme Error Rate of 16.5% and improves upon the state of the art by 1.1% for TIMIT dataset (English) and 11.5% for CSaLT dataset (Urdu).

Omer Beg, Muhammad Nasir Zafar, Waleed Anjum

Text generation tasks have gotten the attention of researchers in the last few years because of their applications on a large scale.In the past, many researchers focused on task-based text generations.Our research focuses on text generation based on the ideology and style of a specific author, and text generation on a topic that was not written by the same author in the past.Our trained model requires an input prompt containing initial few words of text to produce a few paragraphs of text based on the ideology and style of the author on which the model is trained.Our methodology to accomplish this task is based on Bi-LSTM.The Bi-LSTM model is used to make predictions at the character level, during the training corpus of a specific author is used along with the ground truth corpus.A pre-trained model is used to identify the sentences of ground truth having contradiction with the author's corpus to make our language model inclined.During training, we have achieved a perplexity score of 2.23 at the character level. The experiments show a perplexity score of around 3 over the test dataset.