# Non-native Children's Automatic Speech Assessment Challenge (NOCASA)

arXiv: https://arxiv.org/abs/2504.20678 · HTML: https://mlsanity.com/paper/2504.20678/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 29 Apr 2025.

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

- [The SLT 2021 children speech recognition challenge: Open datasets, rules and baselines](https://mlsanity.com/paper/2011.06724/) (2020)
- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Boosting Norwegian Automatic Speech Recognition](https://mlsanity.com/paper/2307.01672/) (2023)
- [On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations](https://mlsanity.com/paper/2406.18065/) (2024)

## Built on by (most cited first, 1 of 1)

- [Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge](https://mlsanity.com/paper/2509.03256/) (2025)

## Abstract (arXiv)

This paper presents the "Non-native Children's Automatic Speech Assessment" (NOCASA) - a data competition part of the IEEE MLSP 2025 conference. NOCASA challenges participants to develop new systems that can assess single-word pronunciations of young second language (L2) learners as part of a gamified pronunciation training app. To achieve this, several issues must be addressed, most notably the limited nature of available training data and the highly unbalanced distribution among the pronunciation level categories. To expedite the development, we provide a pseudo-anonymized training data (TeflonNorL2), containing 10,334 recordings from 44 speakers attempting to pronounce 205 distinct Norwegian words, human-rated on a 1 to 5 scale (number of stars that should be given in the game). In addition to the data, two already trained systems are released as official baselines: an SVM classifier trained on the ComParE_16 acoustic feature set and a multi-task wav2vec 2.0 model. The latter achieves the best performance on the challenge test set, with an unweighted average recall (UAR) of 36.37%.