---
title: "Exploring Non-Autoregressive End-To-End Neural Modeling For"
description: "The authors replace the autoregressive recognizer with a non-autoregressive \"dictation model\" built on… 30 references, cited by 1 paper here."
authors: ["Hsin-Wei Wang", "Bi-Cheng Yan", "Hsuan-Sheng Chiu", "Yung-Chang Hsu", "Berlin Chen"]
year: 2021
venue: "arXiv:2111.00844"
source: "https://arxiv.org/abs/2111.00844"
doi: "10.48550/arxiv.2111.00844"
arxiv: "2111.00844"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2021-exploring-non-autoregressive-end-end/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2021-exploring-non-autoregressive-end-end/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/9/) / Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosis

# Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosis

**Authors:** [Hsin-Wei Wang](https://md.research.elamur.ai/free/en/authors/hsin-wei-wang/), [Bi-Cheng Yan](https://md.research.elamur.ai/free/en/authors/bi-cheng-yan/), Hsuan-Sheng Chiu, [Yung-Chang Hsu](https://md.research.elamur.ai/free/en/authors/yung-chang-hsu/) and [Berlin Chen](https://md.research.elamur.ai/free/en/authors/berlin-chen/) · **Year:** 2021 · **Venue:** arXiv:2111.00844 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2111.00844) · [PDF](https://arxiv.org/pdf/2111.00844) · [DOI 10.48550/arxiv.2111.00844](https://doi.org/10.48550/arxiv.2111.00844) · [arXiv 2111.00844](https://arxiv.org/abs/2111.00844) · [OpenAlex](https://openalex.org/W4291331905)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper targets computer-assisted pronunciation training. The task is to find phone-level mispronunciations in L2 English speech and say what went wrong (MD&D). Common end-to-end systems such as CTC-ATT decode phones left to right with beam search. That makes them slow, and they also suffer when non-native training data is scarce.

The authors replace the autoregressive recognizer with a non-autoregressive "dictation model" built on Mask-CTC. A Conformer encoder with CTC produces an initial phone string. Phones with low confidence are then masked and refilled in parallel by a conditional masked language model that sees context on both sides.

On top of this they add a separate "pronunciation model". It takes the dictated phones and their confidence scores and checks them against the canonical phones of the prompt text, using a prompt-modulated gating mechanism. The system is trained on L2-ARCTIC plus TIMIT.

With wav2vec 2.0 features, the dictation model comes close to the phone error rate of CTC-ATT at a small fraction of its real-time factor. This shows that fast, deployable feedback for learners is feasible.

## Key points
- **Data.** L2-ARCTIC covers 24 non-native speakers with six mother tongues: Hindi, Korean, Mandarin, Spanish, Arabic and Vietnamese.
  - Split by speakers: 17 train, 1 dev and 6 test, with 900 test utterances.
  - TIMIT native speech was pooled into training.
- **Phone inventory.** Training uses 48 phones, each paired with an "anti-phone" that marks distorted, in-between realizations. At test time the inventory is collapsed to 39 phones to stay comparable with earlier work.
- **Dictation model.** It is trained with a joint CTC plus mask-predict objective, using Mask-CTC with a Conformer encoder and a Transformer-based CMLM.
- **Pronunciation model.** Each phone embedding is concatenated with its confidence score and passed through a Transformer encoder. A GRU turns the canonical prompt phones into one embedding, which gates every phone vector through sigmoid gating and ReLU. A final FFN with softmax makes the decision.
- **Speed and accuracy.** On L2-ARCTIC, accuracy is measured as PER (the share of phones recognized wrongly) and speed as RTF (the real-time factor):

  | Model | PER | RTF |
  |---|---|---|
  | CTC-ATT, beam 1 | 15.2% | 3.10 |
  | CTC-ATT, beam 10 | 14.9% | 13.85 |
  | Mask-CTC, FBANK features | 22.6% | 0.05 |
  | Mask-CTC, wav2vec 2.0 features | 15.9% | 0.05 |

  The choice of acoustic features clearly matters for accuracy, while speed stays the same.

## Interesting ideas
- **Draft, mask, refill.** Make a fast first draft of the whole sequence, mask only the low-confidence items, and refill them in parallel from confident context on both sides; this avoids slow sequential decoding while still fixing weak spots.
- **Separate recognizing from judging.** Instead of directly diffing the recognized output against the reference, a second model decides correctness from the output, its confidence and the reference, which makes it robust to a recognizer that overfits.
- **Anti-labels for in-between errors.** Each canonical class gets a companion label for "distorted version of X", so non-categorical errors are not forced into a wrong class.
- **Reference-conditioned gating.** A single summary vector of the expected reference gates every element of the observed sequence, so each item is judged relative to what should have been there.
- **Train fine, evaluate coarse.** Train on a fine-grained label set but collapse it to a standard coarser set for evaluation, keeping detail internally while staying comparable to prior work.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tree): gparse could emit a full parse, mask arcs or labels below a confidence threshold, and re-predict only those given the confident arcs, logging each revision as an explainable repair.
- **I2** (learn): a judge that sees a parse, per-arc confidence and the witness parsers' outputs could decide which arcs enter silver data, rather than relying on plain agreement counts.
- **I3** (tokens): the tagger and morphology could carry an "off-form of X" tag for misspellings, dialect or learner forms, keeping the intended lemma while flagging the deviation.
- **I4** (answer): when grading student answers in school-course tests, the frames of the expected answer could gate how each extracted student frame is scored, with the gate values kept as an explanation.
- **I5** (learn): train on Mova's richer internal relation labels but report on collapsed plain UD labels, so benchmark numbers stay comparable without losing internal distinctions.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [National Taiwan Normal University](https://md.research.elamur.ai/free/en/universities/national-taiwan-normal-university/) — University, Taipei, Taiwan · 7 works · 119 citations
- [Chunghwa Telecom](https://md.research.elamur.ai/free/en/companies/chunghwa-telecom/) — Company, Taipei, Taiwan · 2 works · 2 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 493 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works

## Cite

Cite as: Hsin-Wei Wang, Bi-Cheng Yan, Hsuan-Sheng Chiu, Yung-Chang Hsu and Berlin Chen. 2021. Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosis. arXiv:2111.00844.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{wang2021exploring,
  title = {{Exploring Non-Autoregressive End-To-End Neural Modeling For English Mispronunciation Detection And Diagnosis}},
  author = {Hsin-Wei Wang, Bi-Cheng Yan, Hsuan-Sheng Chiu, Yung-Chang Hsu and Berlin Chen},
  year = {2021},
  doi = {10.48550/arxiv.2111.00844},
  eprint = {2111.00844},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2111.00844}
}
```

- [← previous Evaluating Universal Dependency Parser Recovery of Predicate Argument Structure via CompChain Analysis](https://md.research.elamur.ai/free/en/papers/indurkhya-2021-evaluating-universal-dependency-parser-recovery/)
- [next → False resultatives: The interaction of agreement and creation in Northern Galilee Levantine Arabic](https://md.research.elamur.ai/free/en/papers/rapoport-2021-false-resultatives-interaction-agreement-creation/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/9/)

## References

30 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. K. Evanini and X. Wang, “Automated speech scoring for Non-native middle school students with multiple task types,” in Proceedings of INTERSPEECH, pp. 2435–2439, 2013. [find](https://scholar.google.com/scholar?q=K%2E+Evanini+and+X%2E+Wang%2C+%E2%80%9CAutomated+speech+scoring+for+Non%2Dnative+middle+school+students+with+multiple+task+types%2C%E2%80%9D+in+Proceedings+of+INTERSPEECH%2C+pp%2E+2435%E2%80%932439%2C+2013%2E)
2. A. Metallinou and J. Cheng, “Using deep neural networks to improve proficiency assessment for children English language learners,” in Proceedings of INTERSPEECH, pp. 1468–1472, 2014. [find](https://scholar.google.com/scholar?q=A%2E+Metallinou+and+J%2E+Cheng%2C+%E2%80%9CUsing+deep+neural+networks+to+improve+proficiency+assessment+for+children+English+language+learners%2C%E2%80%9D+in+Proceedings+of+INTERSPEECH%2C+pp%2E+1468%E2%80%931472%2C+2014%2E)
3. H. Li, S. Huang, S. Wang, and B. Xu, “Context-dependent duration modeling with backoff strategy and look-up tables for pronunciation assessment and mispronunciation detection,” in Proceedings of INTERSPEECH, pp. 1133–1136, 2011. [find](https://scholar.google.com/scholar?q=H%2E+Li%2C+S%2E+Huang%2C+S%2E+Wang%2C+and+B%2E+Xu%2C+%E2%80%9CContext%2Ddependent+duration+modeling+with+backoff+strategy+and+look%2Dup+tables+for+pronunciation+assessment+and+mispronunciation+detection%2C%E2%80%9D+in+Proceedings+of+INTER)
4. K. Li, X. Qian, and H. Meng, “Mispronunciation detection and diagnosis in l2 English speech using multidistribution deep neural networks,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 25, no. 1, pp. 193–207, 2017. [↗](https://doi.org/10.1109/taslp.2016.2621675)
5. S. Sudhakara, M. K. Ramanathi, C. Yarra, and P. K. Ghosh, “An improved goodness of pronunciation (GOP) measure for pronunciation evaluation with DNN-HMM system considering hmm transition probabilities.” in Proceedings of INTERSPEECH, 2019, pp. 954–958. [find](https://scholar.google.com/scholar?q=S%2E+Sudhakara%2C+M%2E+K%2E+Ramanathi%2C+C%2E+Yarra%2C+and+P%2E+K%2E+Ghosh%2C+%E2%80%9CAn+improved+goodness+of+pronunciation+%28GOP%29+measure+for+pronunciation+evaluation+with+DNN%2DHMM+system+considering+hmm+transition+probabilities)
6. S. Cheng, Z. Liu, L. Li, Z. Tang, D. Wang, and T. F. Zheng, “ASR-free pronunciation assessment,” in arXiv preprint arXiv:2005.11902, 2020. [↗](https://arxiv.org/abs/2005.11902)
7. Z. Wang, John H.L. Hansen, and Y. Xie, “A multi-view approach for Mandarin non-native mispronunciation verification,” in Proceedings of ICASSP, pp. 8079–8083, 2020. [↗](https://doi.org/10.48550/arxiv.2009.02573)
8. N. Minematsu, “Pronunciation assessment based upon the phonological distortions observed in language learners' utterances,” in Proceedings of INTERSPEECH, pp. 1669–1672, 2004. [find](https://scholar.google.com/scholar?q=N%2E+Minematsu%2C+%E2%80%9CPronunciation+assessment+based+upon+the+phonological+distortions+observed+in+language+learners%27+utterances%2C%E2%80%9D+in+Proceedings+of+INTERSPEECH%2C+pp%2E+1669%E2%80%931672%2C+2004%2E)
9. A. Lee, and J. R. Glass, “Pronunciation assessment via a comparison-based system,” in Proceedings of IEEE SLaTE Workshop, pp. 122–126, 2013. [find](https://scholar.google.com/scholar?q=A%2E+Lee%2C+and+J%2E+R%2E+Glass%2C+%E2%80%9CPronunciation+assessment+via+a+comparison%2Dbased+system%2C%E2%80%9D+in+Proceedings+of+IEEE+SLaTE+Workshop%2C+pp%2E+122%E2%80%93126%2C+2013%2E)
10. W. Leung, X. Liu, and H. Meng, “CNN-RNN-CTC based end-to-end mispronunciation detection and diagnosis,” in Proceedings of ICASSP, pp. 8132–8136, 2019. [find](https://scholar.google.com/scholar?q=W%2E+Leung%2C+X%2E+Liu%2C+and+H%2E+Meng%2C+%E2%80%9CCNN%2DRNN%2DCTC+based+end%2Dto%2Dend+mispronunciation+detection+and+diagnosis%2C%E2%80%9D+in+Proceedings+of+ICASSP%2C+pp%2E+8132%E2%80%938136%2C+2019%2E)
11. K. Fu, J. Lin, D. Ke, Y. Xie, J. Zhang, and B. Lin, “A full text-dependent end to end mispronunciation detection and diagnosis with easy data augmentation techniques,” in arXiv preprint arXiv:2104.08428, 2021. [↗](https://arxiv.org/abs/2104.08428)
12. Y. Feng, G. Fu, Q. Chen, and K. Chen, “SED-MDD: Towards sentence dependent end-to-end mispronunciation detection and diagnosis,” in Proceedings of ICASSP, pp. 3492–3496, 2020. [find](https://scholar.google.com/scholar?q=Y%2E+Feng%2C+G%2E+Fu%2C+Q%2E+Chen%2C+and+K%2E+Chen%2C+%E2%80%9CSED%2DMDD%3A+Towards+sentence+dependent+end%2Dto%2Dend+mispronunciation+detection+and+diagnosis%2C%E2%80%9D+in+Proceedings+of+ICASSP%2C+pp%2E+3492%E2%80%933496%2C+2020%2E)
13. T.-H. Lo, S.-Y. Weng, H.-J. Chang, and B. Chen, “An effective end-to-end modeling approach for mispronunciation detection,” in Proceedings of INTERSPEECH, pp. 3027–3031, 2020. [find](https://scholar.google.com/scholar?q=T%2E%2DH%2E+Lo%2C+S%2E%2DY%2E+Weng%2C+H%2E%2DJ%2E+Chang%2C+and+B%2E+Chen%2C+%E2%80%9CAn+effective+end%2Dto%2Dend+modeling+approach+for+mispronunciation+detection%2C%E2%80%9D+in+Proceedings+of+INTERSPEECH%2C+pp%2E+3027%E2%80%933031%2C+2020%2E)
14. B.-C. Yan, M.-C. Wu, H.-T. Hung, and B. Chen, “[An end-to-end mispronunciation detection system for l2 English speech leveraging novel anti-phone modeling](https://md.research.elamur.ai/free/en/papers/yan-2020-end-end-mispronunciation-detection-system/),” in Proceedings of INTERSPEECH, pp. 3032-3036, 2020.
15. A. Graves, S. Fernández, F. Gomez, and J. Schmidhuber, “Connectionist Temporal Classification: Labelling unsegmented sequence data with recurrent neural networks,” in Proceedings of ICML, pp. 369–376, 2006. [find](https://scholar.google.com/scholar?q=A%2E+Graves%2C+S%2E+Fern%C3%A1ndez%2C+F%2E+Gomez%2C+and+J%2E+Schmidhuber%2C+%E2%80%9CConnectionist+Temporal+Classification%3A+Labelling+unsegmented+sequence+data+with+recurrent+neural+networks%2C%E2%80%9D+in+Proceedings+of+ICML%2C+pp%2E+369%E2%80%93376%2C)
16. J. Chorowski, D. Bahdanau, K. Cho, and Y. Bengio, “End-to-end continuous speech recognition using attention-based recurrent nn: First results,” in arXiv preprint arXiv:1412.1602, 2014. [↗](https://arxiv.org/abs/1412.1602)
17. J. Chorowski, D. Bahdanau, D. Serdyuk, K. Cho, and Y. Bengio, “[Attention-based models for speech recognition](https://md.research.elamur.ai/free/en/papers/chorowski-2015-attention-based-models-speech-recognition/),” in Proceedings of NIPS, pp. 577–585, 2015. [↗](https://doi.org/10.48550/arxiv.1506.07503)
18. D. Bahdanau, J. Chorowski, D. Serdyuk, P. Brakel, and Y. Bengio, “End-to-end attention-based large vocabulary speech recognition,” in Proceedings of ICASSP, pp. 4945-4949, 2016. [find](https://scholar.google.com/scholar?q=D%2E+Bahdanau%2C+J%2E+Chorowski%2C+D%2E+Serdyuk%2C+P%2E+Brakel%2C+and+Y%2E+Bengio%2C+%E2%80%9CEnd%2Dto%2Dend+attention%2Dbased+large+vocabulary+speech+recognition%2C%E2%80%9D+in+Proceedings+of+ICASSP%2C+pp%2E+4945%2D4949%2C+2016%2E)
19. S. Kim, T. Hori, and S. Watanabe, “Joint CTC-attention based end-to-end speech recognition using multi-task learning,” in Proceedings of ICASSP, pp. 4835–4839, 2017. [find](https://scholar.google.com/scholar?q=S%2E+Kim%2C+T%2E+Hori%2C+and+S%2E+Watanabe%2C+%E2%80%9CJoint+CTC%2Dattention+based+end%2Dto%2Dend+speech+recognition+using+multi%2Dtask+learning%2C%E2%80%9D+in+Proceedings+of+ICASSP%2C+pp%2E+4835%E2%80%934839%2C+2017%2E)
20. A. Vaswani, N. Shazeer, N. Parmar, and J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser and I. Polosukhin, “[Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/),” in Proceedings of NIPS, pp. 5998–6008., 2017.
21. Y. Higuchi, S. Watanabe, N. Chen, T. Ogawa, T. Kobayashi, “Mask CTC: Non-autoregressive end-to-end ASR with CTC and mask predict,” in Proceedings of INTERSPEECH, pp. 3655–3659, 2020. [find](https://scholar.google.com/scholar?q=Y%2E+Higuchi%2C+S%2E+Watanabe%2C+N%2E+Chen%2C+T%2E+Ogawa%2C+T%2E+Kobayashi%2C+%E2%80%9CMask+CTC%3A+Non%2Dautoregressive+end%2Dto%2Dend+ASR+with+CTC+and+mask+predict%2C%E2%80%9D+in+Proceedings+of+INTERSPEECH%2C+pp%2E+3655%E2%80%933659%2C+2020%2E)
22. Y. Bai, J. Yi, J. Tao, Z. Tian, Z. Wen, and S. Zhang, “Listen attentively, and spell once: whole sentence generation via a non-autoregressive architecture for low-latency speech recognition,” in Proceedings of INTERSPEECH, pp. 3381– 3385, 2020. [find](https://scholar.google.com/scholar?q=Y%2E+Bai%2C+J%2E+Yi%2C+J%2E+Tao%2C+Z%2E+Tian%2C+Z%2E+Wen%2C+and+S%2E+Zhang%2C+%E2%80%9CListen+attentively%2C+and+spell+once%3A+whole+sentence+generation+via+a+non%2Dautoregressive+architecture+for+low%2Dlatency+speech+recognition%2C%E2%80%9D+in+Proce)
23. E. A. Chi, J. Salazar, and K. Kirchhoff, “Align-Refine: Non-autoregressive speech recognition via iterative realignment,” in Proceedings of NAACL, pp. 1920–1927, 2021. [↗](https://doi.org/10.48550/arxiv.2010.14233)
24. A. Gulati, J. Qin, C. C. Chiu, N. Parmar, Y. Zhang, J. Yu, W. Han, S. Wang, Z. Zhang, Y. Wu, and R. Pang, “[Conformer: Convolution-augmented Transformer for speech recognition](https://md.research.elamur.ai/free/en/papers/gulati-2020-conformer-convolution-augmented-transformer-speech/),” in Proceedings of INTERSPEECH, pp. 4036–5040, 2020.
25. M. Ghazvininejad, O. Levy, Y. Liu, and L. Zettlemoyer, “[Mask-Predict: Parallel decoding of conditional masked language models](https://md.research.elamur.ai/free/en/papers/ghazvininejad-2019-mask-predict-parallel-decoding-conditional/),” in Proceedings of EMNLP-IJCNLP, pp. 6112–6121, 2019.
26. G. Zhao, S. Sonsaat, A. O. Silpachai, I. Lucic, E. Chukharev-Hudilainen, J. Levis, and R. Gutierrez-Osuna, “L2-ARCTIC: A non-native English speech corpus,” Perception Sensing Instrumentation Lab, 2018. [find](https://scholar.google.com/scholar?q=G%2E+Zhao%2C+S%2E+Sonsaat%2C+A%2E+O%2E+Silpachai%2C+I%2E+Lucic%2C+E%2E+Chukharev%2DHudilainen%2C+J%2E+Levis%2C+and+R%2E+Gutierrez%2DOsuna%2C+%E2%80%9CL2%2DARCTIC%3A+A+non%2Dnative+English+speech+corpus%2C%E2%80%9D+Perception+Sensing+Instrumentation+Lab%2C+2018)
27. J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, and D. S. Pallett, “DARPA TIMIT acoustic-phonetic continuous speech corpus CD-Rom: NIST speech disc 1-1.1,” NASA STI/Recon Technical Report, vol. 93, pp. 27403, 1993. [find](https://scholar.google.com/scholar?q=J%2E+S%2E+Garofolo%2C+L%2E+F%2E+Lamel%2C+W%2E+M%2E+Fisher%2C+J%2E+G%2E+Fiscus%2C+and+D%2E+S%2E+Pallett%2C+%E2%80%9CDARPA+TIMIT+acoustic%2Dphonetic+continuous+speech+corpus+CD%2DRom%3A+NIST+speech+disc+1%2D1%2E1%2C%E2%80%9D+NASA+STI%2FRecon+Technical+Report%2C+vo)
28. A. Baevski, H. Zhou, A. Mohamed, and M. Auli, “[wav2vec 2.0: A framework for self-supervised learning of speech representations](https://md.research.elamur.ai/free/en/papers/baevski-2020-wav2vec-2-0-framework-self/),” arXiv preprint arXiv:2006.11477, 2020. [↗](https://arxiv.org/abs/2006.11477)
29. S.-W. Fan Jiang, B.-C. Yan, T.-H. Lo, F.-A. Chao, and B. Chen, “[Towards robust mispronunciation detection and diagnosis for L2 English learners with accent-modulating methods](https://md.research.elamur.ai/free/en/papers/jiang-2021-towards-robust-mispronunciation-detection-diagnosis/),” in Proceedings of ASRU, pp. 1065–1070, 2021.
30. T.-H. Lo, Y.-T. Sung, and B. Chen, “Improving end-to-end modeling for mispronunciation detection with effective augmentation mechanisms,” in Proceedings of APSIPA ASC, pp. 1049–1055, 2021. [↗](https://doi.org/10.48550/arxiv.2110.08731)

*Updated 2 November 2026*