mlsanityData to 14 Oct 2026

Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment

arXiv 2205.03432 ↗First posted 6 May 2022cs.SD cs.LG eess.AScited by 37

Not on the map. Why?

Abstract (arXiv)

Automatic pronunciation assessment is an important technology to help self-directed language learners. While pronunciation quality has multiple aspects including accuracy, fluency, completeness, and prosody, previous efforts typically only model one aspect (e.g., accuracy) at one granularity (e.g., at the phoneme-level). In this work, we explore modeling multi-aspect pronunciation assessment at multiple granularities. Specifically, we train a Goodness Of Pronunciation feature-based Transformer (GOPT) with multi-task learning. Experiments show that GOPT achieves the best results on speechocean762 with a public automatic speech recognition (ASR) acoustic model trained on Librispeech.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 6 of its 27 references that are in the map. First posted on arXiv 6 May 2022.

Builds on

6 of 27 references.

References · 6

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 226
  4. 2021speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessmentcited by 58
  5. 2020Context-aware Goodness of Pronunciation for Computer-Assisted Pronunciation Trainingcited by 26
  6. 2018Investigating the role of L1 in automatic pronunciation evaluation of L2 speechcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 3; 2025: 11; 2026: 10.

37 papers.

Sort:

By area:

  1. 2025ZIPA: A family of efficient models for multilingual phone recognitioncited by 19
  2. 2025Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessmentcited by 15
  3. 2022Hierarchical Pronunciation Assessment with Multi-Aspect Attentioncited by 13
  4. 2023MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarioscited by 8
  5. 2023Automatic Pronunciation Assessment -- A Reviewcited by 7
  6. 2025Towards Efficient and Multifaceted Computer-assisted Pronunciation Training Leveraging Hierarchical Selective State Space Model and Decoupled Cross-entropy Losscited by 6
  7. 2023Zero-Shot Automatic Pronunciation Assessmentcited by 5
  8. 2023Score-balanced Loss for Multi-aspect Pronunciation Assessmentcited by 4
  9. 2024Pronunciation Assessment with Multi-modal Large Language Modelscited by 4
  10. 2023Phonetic and Prosody-aware Self-supervised Learning Approach for Non-native Fluency Scoringcited by 3
  11. 2023Addressing Cold Start Problem for End-to-end Automatic Speech Scoringcited by 3
  12. 2023L1-aware Multilingual Mispronunciation Detection Frameworkcited by 3
25 more
  1. 2023Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessmentcited by 3
  2. 2024Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessmentcited by 3
  3. 2022SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generationcited by 2
  4. 2023Flowchase: a Mobile Application for Pronunciation Trainingcited by 2
  5. 2026Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunitiescited by 2
  6. 2026Self-supervised Speech Comparison for L2 Phone, Rhythm, and Intonation Scoringcited by 2
  7. 2023The complementary roles of non-verbal cues for Robust Pronunciation Assessmentcited by 1
  8. 2025Automated evaluation of children's speech fluency for low-resource languagescited by 1
  9. 2025Evaluating Logit-Based GOP Scores for Mispronunciation Detectioncited by 1
  10. 2025Segmentation-free Goodness of Pronunciationcited by 1
  11. 2025English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLMcited by 1
  12. 2025Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessmentcited by 1
  13. 2026A Finetuned SpeechLLM for Joint Multi-Granular L2 Assessment and Natural-Language Rationalescited by 1
  14. 2026Scaling Human and G2P Supervision for Robust Phonetic Transcriptioncited by 1
  15. 2023Mispronunciation detection using self-supervised speech representationscited by 0
  16. 2024Semi-supervised Learning For Robust Speech Evaluationcited by 0
  17. 2025JCAPT: A Joint Modeling Approach for CAPTcited by 0
  18. 2025Multi-task Pretraining for Enhancing Interpretable L2 Pronunciation Assessmentcited by 0
  19. 2025MuFFIN: Multifaceted Pronunciation Feedback Model with Interactive Hierarchical Neural Modelingcited by 0
  20. 2026Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessmentcited by 0
  21. 2026Goodness-of-pronunciation without phoneme time alignmentcited by 0
  22. 2026Light-weight Pronunciation Assessment via Discrete Speech Token Surprisalcited by 0
  23. 2026A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challengescited by 0
  24. 2026When Speech Meets Lips: Interpretable Audio-Visual Synchronization for L2 Pronunciation Assessmentcited by 0
  25. 2026OpenPA: Forced-alignment-free Multi-granular Pronunciation Assessment with Mixed-transcript Adaptationcited by 0