PronouncUR: An Urdu Pronunciation Lexicon Generator

TL;DR

This paper introduces PronouncUR, an Urdu pronunciation lexicon generator using an LSTM model trained on a handcrafted lexicon, enabling speech recognition development in low-resource Urdu language without expert linguistic input.

Contribution

It presents a novel LSTM-based grapheme-to-phoneme conversion tool for Urdu that reduces reliance on linguistic expertise for speech recognition resources.

Findings

Achieved 64% pronunciation prediction accuracy.

Word error rate comparable to handcrafted lexicons in speech recognition.

Demonstrated feasibility of automated lexicon generation for low-resource languages.

Abstract

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.