PronouncUR: An Urdu Pronunciation Lexicon Generator
This work addresses the lack of linguistic resources for Urdu speech recognition, enabling lexicon generation without expert knowledge, though it is incremental as it builds on existing LSTM methods.
The authors tackled the problem of generating pronunciation lexicons for Urdu, a low-resource language, by developing a grapheme-to-phoneme conversion tool using an LSTM model trained on 39,000 expert-annotated words, achieving 64% accuracy in internal evaluation and a word error rate comparable to a handcrafted lexicon in speech recognition tasks.
State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise, which is a barrier in low-resource domains. Techniques to construct these three components without having expert domain knowledge are in great demand. Urdu, despite having millions of speakers all over the world, is a low-resource language in terms of standard publically available linguistic resources. In this paper, we present a grapheme-to-phoneme conversion tool for Urdu that generates a pronunciation lexicon in a form suitable for use with speech recognition systems from a list of Urdu words. The tool predicts the 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. For external evaluation on a speech recognition task, we obtain a word error rate comparable to one achieved using a fully handcrafted expert lexicon.