# The NTNU System at the S&I Challenge 2025 SLA Open Track

arXiv: https://arxiv.org/abs/2506.05121 · HTML: https://mlsanity.com/paper/2506.05121/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens](https://mlsanity.com/paper/2402.13753/) (2024)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [Can Large Language Models Automatically Score Proficiency of Written Essays?](https://mlsanity.com/paper/2403.06149/) (2024)
- [Self-attention encoding and pooling for speaker recognition](https://mlsanity.com/paper/2008.01077/) (2020)
- [Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2204.03863/) (2022)
- [Proficiency assessment of L2 spoken English using wav2vec 2.0](https://mlsanity.com/paper/2210.13168/) (2022)
- [Speak & Improve Corpus 2025: an L2 English Speech Corpus for Language Assessment and Feedback](https://mlsanity.com/paper/2412.11986/) (2024)
- [Speak & Improve Challenge 2025: Tasks and Baseline Systems](https://mlsanity.com/paper/2412.11985/) (2024)
- [LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Models](https://mlsanity.com/paper/2505.08498/) (2025)
- [An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution](https://mlsanity.com/paper/2404.07575/) (2024)
- [L2 proficiency assessment using self-supervised speech representations](https://mlsanity.com/paper/2211.08849/) (2022)

## Built on by (most cited first, 3 of 3)

- [Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning](https://mlsanity.com/paper/2509.16025/) (2025)
- [LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment](https://mlsanity.com/paper/2606.31310/) (2026)
- [Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors](https://mlsanity.com/paper/2608.06300/) (2026)

## Abstract (arXiv)

A recent line of research on spoken language assessment (SLA) employs neural models such as BERT and wav2vec 2.0 (W2V) to evaluate speaking proficiency across linguistic and acoustic modalities. Although both models effectively capture features relevant to oral competence, each exhibits modality-specific limitations. BERT-based methods rely on ASR transcripts, which often fail to capture prosodic and phonetic cues for SLA. In contrast, W2V-based methods excel at modeling acoustic features but lack semantic interpretability. To overcome these limitations, we propose a system that integrates W2V with Phi-4 multimodal large language model (MLLM) through a score fusion strategy. The proposed system achieves a root mean square error (RMSE) of 0.375 on the official test set of the Speak & Improve Challenge 2025, securing second place in the competition. For comparison, the RMSEs of the top-ranked, third-ranked, and official baseline systems are 0.364, 0.384, and 0.444, respectively.