# Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

arXiv: https://arxiv.org/abs/2301.06736 · HTML: https://mlsanity.com/paper/2301.06736/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 17 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights](https://mlsanity.com/paper/2106.05852/) (2021)
- [An investigation of phone-based subword units for end-to-end speech recognition](https://mlsanity.com/paper/2004.04290/) (2020)
- [Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition](https://mlsanity.com/paper/2104.09106/) (2021)
- [A Comparison of Methods for OOV-word Recognition on a New Public Dataset](https://mlsanity.com/paper/2107.08091/) (2021)

## Abstract (arXiv)

In a hybrid automatic speech recognition (ASR) system, a pronunciation lexicon (PL) and a language model (LM) are essential to correctly retrieve spoken word sequences. Being a morphologically complex language, the vocabulary of Malayalam is so huge and it is impossible to build a PL and an LM that cover all diverse word forms. Usage of subword tokens to build PL and LM, and combining them to form words after decoding, enables the recovery of many out of vocabulary words. In this work we investigate the impact of using syllables as subword tokens instead of words in Malayalam ASR, and evaluate the relative improvement in lexicon size, model memory requirement and word error rate.