# Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil

arXiv: https://arxiv.org/abs/2107.03675 · HTML: https://mlsanity.com/paper/2107.03675/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 36 references that are in the map.
- First posted on arXiv 8 Jul 2021.

## Builds on (most cited first, 3 of 3)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Context-aware Goodness of Pronunciation for Computer-Assisted Pronunciation Training](https://mlsanity.com/paper/2008.08647/) (2020)
- [ASR-Free Pronunciation Assessment](https://mlsanity.com/paper/2005.11902/) (2020)

## Built on by (most cited first, 10 of 10)

- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information](https://mlsanity.com/paper/2203.01826/) (2022)
- [Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring](https://mlsanity.com/paper/2305.11438/) (2023)
- [SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning](https://mlsanity.com/paper/2506.02412/) (2025)
- [The complementary roles of non-verbal cues for Robust Pronunciation Assessment](https://mlsanity.com/paper/2309.07739/) (2023)
- [MultiGen: Child-Friendly Multilingual Speech Generator with LLMs](https://mlsanity.com/paper/2508.08715/) (2025)
- [Multiple output samples per input in a single-output Gaussian process](https://mlsanity.com/paper/2306.02719/) (2023)
- [Semi-supervised Learning For Robust Speech Evaluation](https://mlsanity.com/paper/2409.14666/) (2024)
- [CBF-AFA: Chunk-Based Multi-SSL Fusion for Automatic Fluency Assessment](https://mlsanity.com/paper/2506.20243/) (2025)
- [Goodness-of-pronunciation without phoneme time alignment](https://mlsanity.com/paper/2603.25150/) (2026)

## Abstract (arXiv)

Speech evaluation is an essential component in computer-assisted language learning (CALL). While speech evaluation on English has been popular, automatic speech scoring on low resource languages remains challenging. Work in this area has focused on monolingual specific designs and handcrafted features stemming from resource-rich languages like English. Such approaches are often difficult to generalize to other languages, especially if we also want to consider suprasegmental qualities such as rhythm. In this work, we examine three different languages that possess distinct rhythm patterns: English (stress-timed), Malay (syllable-timed), and Tamil (mora-timed). We exploit robust feature representations inspired by music processing and vector representation learning. Empirical validations show consistent gains for all three languages when predicting pronunciation, rhythm and intonation performance.