Papers by Haris Bin Zia
PronouncUR: An Urdu Pronunciation Lexicon Generator (L18-1)
Copied to clipboard
| Challenge: | acoustic modeling, large text data and a pronunciation lexicon are the bottlenecks for speech recognition systems for resource scarce languages. |
| Approach: | They propose a grapheme-to-phoneme conversion tool that generates a pronunciation lexicon from a list of Urdu words. |
| Outcome: | The proposed tool predicts pronunciation of words using a LSTM-based model trained on a handcrafted expert lexicon of around 39,000 words and shows an accuracy of 64% upon internal evaluation. |
Urdu Word Segmentation using Conditional Random Fields (CRFs) (C18-1)
Copied to clipboard
| Challenge: | Urdu is amongst languages for which word segmentation is a complex task as it exhibits space omission and space insertion issues. |
| Approach: | They propose a word segmentation system for Urdu which uses a Conditional Random Field sequence modeler with orthographic, linguistic and morphological features. |
| Outcome: | The proposed system achieves an F1 score for word boundary identification and 0.85 for sub-word boundary identification tasks. |