# Multi-task Pretraining for Enhancing Interpretable L2 Pronunciation Assessment

arXiv: https://arxiv.org/abs/2509.16876 · HTML: https://mlsanity.com/paper/2509.16876/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [E-Branchformer: Branchformer with Enhanced merging for speech recognition](https://mlsanity.com/paper/2210.00077/) (2022)
- [speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment](https://mlsanity.com/paper/2104.01378/) (2021)
- [PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS](https://mlsanity.com/paper/2103.15060/) (2021)
- [Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment](https://mlsanity.com/paper/2205.03432/) (2022)
- [3M: An Effective Multi-view, Multi-granularity, and Multi-aspect Modeling Approach to English Pronunciation Assessment](https://mlsanity.com/paper/2208.09110/) (2022)
- [XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech](https://mlsanity.com/paper/2305.19709/) (2023)
- [Hierarchical Pronunciation Assessment with Multi-Aspect Attention](https://mlsanity.com/paper/2211.08102/) (2022)
- [A Hierarchical Context-aware Modeling Approach for Multi-aspect and Multi-granular Pronunciation Assessment](https://mlsanity.com/paper/2305.18146/) (2023)
- [Automatic Pronunciation Assessment -- A Review](https://mlsanity.com/paper/2310.13974/) (2023)
- [Phonetically-Oriented Word Error Alignment for Speech Recognition Error Analysis in Speech Translation](https://mlsanity.com/paper/1904.11024/) (2019)
- [Speaker Fluency Level Classification Using Machine Learning Techniques](https://mlsanity.com/paper/1808.10556/) (2018)
- [Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoring](https://mlsanity.com/paper/2305.11438/) (2023)
- [Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment](https://mlsanity.com/paper/2310.01839/) (2023)
- [Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment](https://mlsanity.com/paper/2406.15723/) (2024)

## Abstract (arXiv)

Automatic pronunciation assessment (APA) analyzes second-language (L2) learners' speech by providing fine-grained pronunciation feedback at various linguistic levels. Most existing efforts on APA typically adopt segmental-level features as inputs and predict pronunciation scores at different granularities via hierarchical (or parallel) pronunciation modeling. This, however, inevitably causes assessments across linguistic levels (e.g., phone, word, and utterance) to rely solely on phoneme-level pronunciation features, nearly sidelining supra-segmental pronunciation cues. To address this limitation, we introduce multi-task pretraining (MTP) for APA, a simple yet effective strategy that attempts to capture long-term temporal pronunciation cues while strengthening the intrinsic structures within an utterance via the objective of reconstructing input features. Specifically, for a phoneme-level encoder of an APA model, the proposed MTP strategy randomly masks segmental-level pronunciation features and reconstructs the masked ones based on their surrounding pronunciation context. Furthermore, current APA systems lack integration with automated speaking assessment (ASA), limiting holistic proficiency evaluation. Drawing on empirical studies and prior knowledge in ASA, our framework bridges this gap by incorporating handcrafted features (HCFs), such as fluency (speech rate, silence duration) and stress (pitch accent strength), derived from human-designed formulas via regressors to generate interpretable proficiency scores. Experiments on speechocean762 show improved pronunciation scoring and ASA proficiency correlation, enabling targeted training and comprehensive proficiency assessment.