---
title: "Leveraging Allophony in Self-Supervised Speech Models for"
description: "The authors propose MixGoP, which fits one Gaussian mixture model per phoneme on frozen… 64 references, cited by 5 papers here."
authors: ["Kwanghee Choi", "Eunjung Yeo", "Kalvin Chang", "Shinji Watanabe", "David R Mortensen"]
year: 2025
venue: "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.naacl-long.132/"
doi: "10.18653/v1/2025.naacl-long.132"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/choi-2025-leveraging-allophony-self-supervised-speech/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/choi-2025-leveraging-allophony-self-supervised-speech/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/) / Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment

# Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment

**Authors:** [Kwanghee Choi](https://md.research.elamur.ai/free/en/authors/kwanghee-choi/), Eunjung Yeo, [Kalvin Chang](https://md.research.elamur.ai/free/en/authors/kalvin-chang/), [Shinji Watanabe](https://md.research.elamur.ai/free/en/authors/shinji-watanabe/) and [David R Mortensen](https://md.research.elamur.ai/free/en/authors/david-r-mortensen/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.naacl-long.132/) · [PDF](https://aclanthology.org/2025.naacl-long.132.pdf) · [DOI 10.18653/v1/2025.naacl-long.132](https://doi.org/10.18653/v1/2025.naacl-long.132) · [OpenAlex](https://openalex.org/W4411120560)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/choi-2025-leveraging-allophony-self-supervised-speech/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Assessing atypical pronunciation, such as dysarthric or non-native speech, requires telling unusual realizations of a phoneme apart from normal variation. One phoneme can legitimately surface in several forms depending on context; English /t/, for example, can be aspirated, flapped or glottalized. Recent classifier-based Goodness of Pronunciation (GoP) methods ignore this allophony. They treat each phoneme as one cluster and rely on a softmax, which assumes the test speech resembles the training data.

The authors propose MixGoP, which fits one Gaussian mixture model per phoneme on frozen self-supervised speech model (S3M) features. Each phoneme is modelled as several subclusters, standing in for allophones. Scoring uses the phoneme likelihood directly rather than a softmax posterior, which makes it behave like an out-of-distribution detector.

Models are trained only on healthy or native speech and tested on atypical speech. Across five datasets and eight compared methods, MixGoP reaches state-of-the-art results on four. Further analysis indicates that S3M features represent allophonic variation better than MFCCs or Mel spectrograms. This supports pairing mixture-based scoring with S3Ms for clinical and language-learning assessment.

## Key points
- **Datasets:** three dysarthric corpora (UASpeech, TORGO, SSNCE, the last in Tamil) and two non-native corpora (speechocean762, L2-ARCTIC).
- **Features:**
  - Frozen S3M features from XLS-R-300M and WavLM-Large, taken from every layer (convolutional layer 0 plus Transformer layers 1–24).
  - Baselines: MFCCs, Mel spectrograms and, for speechocean762, TDNN-F features.
- **Training:** each phoneme gets a GMM with a fixed number of components (e.g., C = 32). Components are initialized with k-means and fitted by EM in scikit-learn. The Gaussian quadratic term relates the score to the Mahalanobis distance.
- **Baselines:** classifier-based GoP variants (GMM-GoP, NN-GoP, DNN-GoP, MaxLogit-GoP) and OOD detectors (kNN, one-class SVM, among others).
- **Limitations and availability:**
  - The data is mostly English.
  - Alignment quality was not verified.
  - The allophony analysis relies mainly on TORGO's manual alignments.
  - Code is released on GitHub (juice500ml/acoustic-units-for-ood).

*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

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations

📚 Shelves (8): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 241 works · [🩺 Physiology](https://md.research.elamur.ai/free/en/shelves/medicine/physiology/) · 29 works

## Cite

Cite as: Kwanghee Choi, Eunjung Yeo, Kalvin Chang, Shinji Watanabe and David R Mortensen. 2025. Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

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

```bibtex
@inproceedings{choi2025leveraging,
  title = {{Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment}},
  author = {Kwanghee Choi, Eunjung Yeo, Kalvin Chang, Shinji Watanabe and David R Mortensen},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.132},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.132}
}
```

- [← previous LAQuer: Localized Attribution Queries in Content-grounded Generation](https://md.research.elamur.ai/free/en/papers/hirsch-2025-laquer-localized-attribution-queries-content/)
- [next → LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference](https://md.research.elamur.ai/free/en/papers/hong-2025-litex-linguistic-taxonomy-explanations-understanding/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/)

## References

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

1. B. M Abdullah, M. M. Shaik, B. Möbius, and D. Klakow. 2023. An information-theoretic analysis of self-supervised discrete representations of speech. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=B%2E+M+Abdullah%2C+M%2E+M%2E+Shaik%2C+B%2E+M%C3%B6bius%2C+and+D%2E+Klakow%2E+2023%2E+An+information%2Dtheoretic+analysis+of+self%2Dsupervised+discrete+representations+of+speech%2E+In+Proc%2E+Interspeech%2E)
2. T-H. Feng, A. Dong, C-F Yeh, et al. 2023. SUPERB @ SLT 2022: Challenge on generalization and efficiency of self-supervised speech representation learning. In Proc. SLT. [find](https://scholar.google.com/scholar?q=T%2DH%2E+Feng%2C+A%2E+Dong%2C+C%2DF+Yeh%2C+et+al%2E+2023%2E+SUPERB+%40+SLT+2022%3A+Challenge+on+generalization+and+efficiency+of+self%2Dsupervised+speech+representation+learning%2E+In+Proc%2E+SLT%2E)
3. A. Babu, C. Wang, A. Tjandra, et al. 2022. [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://md.research.elamur.ai/free/en/papers/babu-2021-xls-r-self-supervised-cross/). In Proc. Interspeech.
4. Y. Gong, Z. Chen, I-H. Chu, P. Chang, and J. Glass. 2022. [Transformer-based multi-aspect multi-granularity non-native english speaker pronunciation assessment](https://md.research.elamur.ai/free/en/papers/gong-2022-transformer-based-multi-aspect-multi/). In Proc. ICASSP.
5. A. Baevski, Y. Zhou, A. Mohamed, and M. Auli. 2020. [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/). In Proc. NeurIPS.
6. D. Hendrycks and K. Gimpel. 2017. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In Proc. ICLR. [find](https://scholar.google.com/scholar?q=D%2E+Hendrycks+and+K%2E+Gimpel%2E+2017%2E+A+baseline+for+detecting+misclassified+and+out%2Dof%2Ddistribution+examples+in+neural+networks%2E+In+Proc%2E+ICLR%2E)
7. J.A. Bilmes et al. 1998. A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. International Computer Science Institute. [find](https://scholar.google.com/scholar?q=J%2EA%2E+Bilmes+et+al%2E+1998%2E+A+gentle+tutorial+of+the+em+algorithm+and+its+application+to+parameter+estimation+for+gaussian+mixture+and+hidden+markov+models%2E+International+Computer+Science+Institute%2E)
8. A. Hernandez, E.J. Yeo, S. Kim, and M. Chung. 2020. Dysarthria detection and severity assessment using rhythm-based metrics. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=A%2E+Hernandez%2C+E%2EJ%2E+Yeo%2C+S%2E+Kim%2C+and+M%2E+Chung%2E+2020%2E+Dysarthria+detection+and+severity+assessment+using+rhythm%2Dbased+metrics%2E+In+Proc%2E+Interspeech%2E)
9. M. Blondel, O. Teboul, Q. Berthet, and J. Djolonga. 2020. Fast differentiable sorting and ranking. In Proc. ICML. [find](https://scholar.google.com/scholar?q=M%2E+Blondel%2C+O%2E+Teboul%2C+Q%2E+Berthet%2C+and+J%2E+Djolonga%2E+2020%2E+Fast+differentiable+sorting+and+ranking%2E+In+Proc%2E+ICML%2E)
10. X. Cao, Z. Fan, T Svendsen, and G. Salvi. 2024. A framework for phoneme-level pronunciation assessment using ctc. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=X%2E+Cao%2C+Z%2E+Fan%2C+T+Svendsen%2C+and+G%2E+Salvi%2E+2024%2E+A+framework+for+phoneme%2Dlevel+pronunciation+assessment+using+ctc%2E+In+Proc%2E+Interspeech%2E)
11. W-N. Hsu, B. Bolte, Yao-Hung H. Tsai, et al. 2021. Hu-BERT: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM TASLP. [find](https://scholar.google.com/scholar?q=W%2DN%2E+Hsu%2C+B%2E+Bolte%2C+Yao%2DHung+H%2E+Tsai%2C+et+al%2E+2021%2E+Hu%2DBERT%3A+Self%2Dsupervised+speech+representation+learning+by+masked+prediction+of+hidden+units%2E+IEEE%2FACM+TASLP%2E)
12. W. Hu, Y. Qian, and F. K. Soong. 2015a. An improved dnn-based approach to mispronunciation detection and diagnosis of l2 learners’ speech. In SLaTE. [find](https://scholar.google.com/scholar?q=W%2E+Hu%2C+Y%2E+Qian%2C+and+F%2E+K%2E+Soong%2E+2015a%2E+An+improved+dnn%2Dbased+approach+to+mispronunciation+detection+and+diagnosis+of+l2+learners%E2%80%99+speech%2E+In+SLaTE%2E)
13. X. Chang, B. Yan, K. Choi, et al. 2024. Exploring speech recognition, translation, and understanding with discrete speech units: A comparative study. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=X%2E+Chang%2C+B%2E+Yan%2C+K%2E+Choi%2C+et+al%2E+2024%2E+Exploring+speech+recognition%2C+translation%2C+and+understanding+with+discrete+speech+units%3A+A+comparative+study%2E+In+Proc%2E+ICASSP%2E)
14. W. Hu, Y. Qian, F. K Soong, and Y. Wang. 2015b. Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Communication. [find](https://scholar.google.com/scholar?q=W%2E+Hu%2C+Y%2E+Qian%2C+F%2E+K+Soong%2C+and+Y%2E+Wang%2E+2015b%2E+Improved+mispronunciation+detection+with+deep+neural+network+trained+acoustic+models+and+transfer+learning+based+logistic+regression+classifiers%2E+Speech)
15. F-A. Chao, T-H. Lo, T-I. Wu, et al. 2022. 3m: An effective multi-view, multi-granularity, and multi-aspect modeling approach to english pronunciation assessment. In Proc. APSIPA ASC. [find](https://scholar.google.com/scholar?q=F%2DA%2E+Chao%2C+T%2DH%2E+Lo%2C+T%2DI%2E+Wu%2C+et+al%2E+2022%2E+3m%3A+An+effective+multi%2Dview%2C+multi%2Dgranularity%2C+and+multi%2Daspect+modeling+approach+to+english+pronunciation+assessment%2E+In+Proc%2E+APSIPA+ASC%2E)
16. O. Jokisch, A. Wagner, R. Sabo, et al. 2009. Multilingual speech data collection for the assessment of pronunciation and prosody in a language learning system. In Proc. of SPECOM. [find](https://scholar.google.com/scholar?q=O%2E+Jokisch%2C+A%2E+Wagner%2C+R%2E+Sabo%2C+et+al%2E+2009%2E+Multilingual+speech+data+collection+for+the+assessment+of+pronunciation+and+prosody+in+a+language+learning+system%2E+In+Proc%2E+of+SPECOM%2E)
17. S. Chen, C. Wang, Z. Chen, et al. 2022. Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE JSTSP. [find](https://scholar.google.com/scholar?q=S%2E+Chen%2C+C%2E+Wang%2C+Z%2E+Chen%2C+et+al%2E+2022%2E+Wavlm%3A+Large%2Dscale+self%2Dsupervised+pre%2Dtraining+for+full+stack+speech+processing%2E+IEEE+JSTSP%2E)
18. H. Kim, M. Hasegawa-Johnson, A. Perlman, et al. 2008. Dysarthric speech database for universal access research. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=H%2E+Kim%2C+M%2E+Hasegawa%2DJohnson%2C+A%2E+Perlman%2C+et+al%2E+2008%2E+Dysarthric+speech+database+for+universal+access+research%2E+In+Proc%2E+Interspeech%2E)
19. S. Cheng, Z. Liu, L. Li, et al. 2020. ASR-Free Pronunciation Assessment. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=S%2E+Cheng%2C+Z%2E+Liu%2C+L%2E+Li%2C+et+al%2E+2020%2E+ASR%2DFree+Pronunciation+Assessment%2E+In+Proc%2E+Interspeech%2E)
20. H. Kim, K. Martin, M. Hasegawa-Johnson, and A. Perlman. 2010. Frequency of consonant articulation errors in dysarthric speech. Clinical linguistics & phonetics. [find](https://scholar.google.com/scholar?q=H%2E+Kim%2C+K%2E+Martin%2C+M%2E+Hasegawa%2DJohnson%2C+and+A%2E+Perlman%2E+2010%2E+Frequency+of+consonant+articulation+errors+in+dysarthric+speech%2E+Clinical+linguistics+%26+phonetics%2E)
21. K. Choi, J-W. Jung, and S. Watanabe. 2024a. Understanding probe behaviors through variational bounds of mutual information. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=K%2E+Choi%2C+J%2DW%2E+Jung%2C+and+S%2E+Watanabe%2E+2024a%2E+Understanding+probe+behaviors+through+variational+bounds+of+mutual+information%2E+In+Proc%2E+ICASSP%2E)
22. K. Choi, A. Pasad, T. Nakamura, et al. 2024b. Self-supervised speech representations are more phonetic than semantic. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=K%2E+Choi%2C+A%2E+Pasad%2C+T%2E+Nakamura%2C+et+al%2E+2024b%2E+Self%2Dsupervised+speech+representations+are+more+phonetic+than+semantic%2E+In+Proc%2E+Interspeech%2E)
23. D. P. Kingma and J. Ba. 2015. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). In Proc. ICLR.
24. J. Kominek and A. W. Black. 2004. The cmu arctic speech databases. In Proc. Speech Synthesis Workshop. [find](https://scholar.google.com/scholar?q=J%2E+Kominek+and+A%2E+W%2E+Black%2E+2004%2E+The+cmu+arctic+speech+databases%2E+In+Proc%2E+Speech+Synthesis+Workshop%2E)
25. D. Korzekwa, J. Lorenzo-Trueba, S. Zaporowski, S. Calamaro, T. Drugman, and B. Kostek. 2021. [Mispronunciation detection in non-native (l2) english with uncertainty modeling](https://md.research.elamur.ai/free/en/papers/korzekwa-2021-mispronunciation-detection-non-native-l2/). In Proc. ICASSP.
26. P. Ladefoged. 1965. The nature of general phonetic theories. Monograph Series on Languages and Linguistics, pages 27–42. [find](https://scholar.google.com/scholar?q=P%2E+Ladefoged%2E+1965%2E+The+nature+of+general+phonetic+theories%2E+Monograph+Series+on+Languages+and+Linguistics%2C+pages+27%E2%80%9342%2E)
27. J. Lee, K. Lee, H. Lee, and J. Shin. 2018. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In Proc. NeurIPS. [find](https://scholar.google.com/scholar?q=J%2E+Lee%2C+K%2E+Lee%2C+H%2E+Lee%2C+and+J%2E+Shin%2E+2018%2E+A+simple+unified+framework+for+detecting+out%2Dof%2Ddistribution+samples+and+adversarial+attacks%2E+In+Proc%2E+NeurIPS%2E)
28. K-F. Lee, S. Hayamizu, H-W. Hon, et al. 1990. Allophone clustering for continuous speech recognition. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=K%2DF%2E+Lee%2C+S%2E+Hayamizu%2C+H%2DW%2E+Hon%2C+et+al%2E+1990%2E+Allophone+clustering+for+continuous+speech+recognition%2E+In+Proc%2E+ICASSP%2E)
29. K. Li, X. Qian, and H. Meng. 2016. Mispronunciation detection and diagnosis in l2 english speech using multidistribution deep neural networks. IEEE/ACM TASLP. [find](https://scholar.google.com/scholar?q=K%2E+Li%2C+X%2E+Qian%2C+and+H%2E+Meng%2E+2016%2E+Mispronunciation+detection+and+diagnosis+in+l2+english+speech+using+multidistribution+deep+neural+networks%2E+IEEE%2FACM+TASLP%2E)
30. O. D. Liu, H. Tang, and S. Goldwater. 2023. Self-supervised predictive coding models encode speaker and phonetic information in orthogonal subspaces. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=O%2E+D%2E+Liu%2C+H%2E+Tang%2C+and+S%2E+Goldwater%2E+2023%2E+Self%2Dsupervised+predictive+coding+models+encode+speaker+and+phonetic+information+in+orthogonal+subspaces%2E+In+Proc%2E+Interspeech%2E)
31. L. MacKenzie and D. Turton. 2020. Assessing the accuracy of existing forced alignment software on varieties of british english. Linguistics Vanguard, 6(s1):20180061. [find](https://scholar.google.com/scholar?q=L%2E+MacKenzie+and+D%2E+Turton%2E+2020%2E+Assessing+the+accuracy+of+existing+forced+alignment+software+on+varieties+of+british+english%2E+Linguistics+Vanguard%2C+6%28s1%29%3A20180061%2E)
32. K. Martin, J. Gauthier, C. Breiss, and R. Levy. 2023. Probing Self-supervised Speech Models for Phonetic and Phonemic Information: A Case Study in Aspiration. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=K%2E+Martin%2C+J%2E+Gauthier%2C+C%2E+Breiss%2C+and+R%2E+Levy%2E+2023%2E+Probing+Self%2Dsupervised+Speech+Models+for+Phonetic+and+Phonemic+Information%3A+A+Case+Study+in+Aspiration%2E+In+Proc%2E+Interspeech%2E)
33. M. McAuliffe, M. Socolof, S. Mihuc, M. Wagner, and M. Sonderegger. 2017. Montreal forced aligner: Trainable text-speech alignment using kaldi. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=M%2E+McAuliffe%2C+M%2E+Socolof%2C+S%2E+Mihuc%2C+M%2E+Wagner%2C+and+M%2E+Sonderegger%2E+2017%2E+Montreal+forced+aligner%3A+Trainable+text%2Dspeech+alignment+using+kaldi%2E+In+Proc%2E+Interspeech%2E)
34. B. McFee, C. Raffel, D. Liang, et al. 2015. librosa: Audio and music signal analysis in python. In Proc. Python in Science Conference. [find](https://scholar.google.com/scholar?q=B%2E+McFee%2C+C%2E+Raffel%2C+D%2E+Liang%2C+et+al%2E+2015%2E+librosa%3A+Audio+and+music+signal+analysis+in+python%2E+In+Proc%2E+Python+in+Science+Conference%2E)
35. L. McInnes, J. Healy, N. Saul, and L. Großberger. 2018. Umap: Uniform manifold approximation and projection. The Journal of Open Source Software. [find](https://scholar.google.com/scholar?q=L%2E+McInnes%2C+J%2E+Healy%2C+N%2E+Saul%2C+and+L%2E+Gro%C3%9Fberger%2E+2018%2E+Umap%3A+Uniform+manifold+approximation+and+projection%2E+The+Journal+of+Open+Source+Software%2E)
36. B. K. Ng and P. S. Chiew. 2023. L1 influence on stop consonant production: A case study of malaysian mandarin-english bilinguals. Asian Englishes. [find](https://scholar.google.com/scholar?q=B%2E+K%2E+Ng+and+P%2E+S%2E+Chiew%2E+2023%2E+L1+influence+on+stop+consonant+production%3A+A+case+study+of+malaysian+mandarin%2Denglish+bilinguals%2E+Asian+Englishes%2E)
37. T. Nguyen, H. D. Nguyen, F. Chamroukhi, and G. J. McLachlan. 2020. Approximation by finite mixtures of continuous density functions that vanish at infinity. Cogent Mathematics & Statistics. [find](https://scholar.google.com/scholar?q=T%2E+Nguyen%2C+H%2E+D%2E+Nguyen%2C+F%2E+Chamroukhi%2C+and+G%2E+J%2E+McLachlan%2E+2020%2E+Approximation+by+finite+mixtures+of+continuous+density+functions+that+vanish+at+infinity%2E+Cogent+Mathematics+%26+Statistics%2E)
38. A. Pasad, B. Shi, and K. Livescu. 2023. Comparative layer-wise analysis of self-supervised speech models. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=A%2E+Pasad%2C+B%2E+Shi%2C+and+K%2E+Livescu%2E+2023%2E+Comparative+layer%2Dwise+analysis+of+self%2Dsupervised+speech+models%2E+In+Proc%2E+ICASSP%2E)
39. F. Pedregosa, G. Varoquaux, A. Gramfort, et al. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research. [find](https://scholar.google.com/scholar?q=F%2E+Pedregosa%2C+G%2E+Varoquaux%2C+A%2E+Gramfort%2C+et+al%2E+2011%2E+Scikit%2Dlearn%3A+Machine+learning+in+Python%2E+Journal+of+Machine+Learning+Research%2E)
40. D. Povey, G. Cheng, Y. Wang, et al. 2018. Semi-orthogonal low-rank matrix factorization for deep neural networks. In Proc. Interspeech, pages 3743– 3747. [find](https://scholar.google.com/scholar?q=D%2E+Povey%2C+G%2E+Cheng%2C+Y%2E+Wang%2C+et+al%2E+2018%2E+Semi%2Dorthogonal+low%2Drank+matrix+factorization+for+deep+neural+networks%2E+In+Proc%2E+Interspeech%2C+pages+3743%E2%80%93+3747%2E)
41. F. Rudzicz, A. K. Namasivayam, and T. Wolff. 2012. The torgo database of acoustic and articulatory speech from speakers with dysarthria. Language Resources and Evaluation. [find](https://scholar.google.com/scholar?q=F%2E+Rudzicz%2C+A%2E+K%2E+Namasivayam%2C+and+T%2E+Wolff%2E+2012%2E+The+torgo+database+of+acoustic+and+articulatory+speech+from+speakers+with+dysarthria%2E+Language+Resources+and+Evaluation%2E)
42. S. Sagayama. 1989. Phoneme environment clustering for speech recognition. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=S%2E+Sagayama%2E+1989%2E+Phoneme+environment+clustering+for+speech+recognition%2E+In+Proc%2E+ICASSP%2E)
43. B. Schölkopf, J. C Platt, J. Shawe-Taylor, et al. 2001. Estimating the support of a high-dimensional distribution. Neural computation. [find](https://scholar.google.com/scholar?q=B%2E+Sch%C3%B6lkopf%2C+J%2E+C+Platt%2C+J%2E+Shawe%2DTaylor%2C+et+al%2E+2001%2E+Estimating+the+support+of+a+high%2Ddimensional+distribution%2E+Neural+computation%2E)
44. M. Shahin and B. Ahmed. 2019. Anomaly detection based pronunciation verification approach using speech attribute features. Speech Communication. [find](https://scholar.google.com/scholar?q=M%2E+Shahin+and+B%2E+Ahmed%2E+2019%2E+Anomaly+detection+based+pronunciation+verification+approach+using+speech+attribute+features%2E+Speech+Communication%2E)
45. M. Shahin, J. Epps, and B. Ahmed. 2024. Phonological level wav2vec2-based mispronunciation detection and diagnosis method. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=M%2E+Shahin%2C+J%2E+Epps%2C+and+B%2E+Ahmed%2E+2024%2E+Phonological+level+wav2vec2%2Dbased+mispronunciation+detection+and+diagnosis+method%2E+In+Proc%2E+Interspeech%2E)
46. J. Shi, N. Huo, and Q. Jin. 2020. Context-aware goodness of pronunciation for computer-assisted pronunciation training. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=J%2E+Shi%2C+N%2E+Huo%2C+and+Q%2E+Jin%2E+2020%2E+Context%2Daware+goodness+of+pronunciation+for+computer%2Dassisted+pronunciation+training%2E+In+Proc%2E+Interspeech%2E)
47. A. Sicherman and Y. Adi. 2023. Analysing discrete self supervised speech representation for spoken language modeling. In Proc. ICASSP. [find](https://scholar.google.com/scholar?q=A%2E+Sicherman+and+Y%2E+Adi%2E+2023%2E+Analysing+discrete+self+supervised+speech+representation+for+spoken+language+modeling%2E+In+Proc%2E+ICASSP%2E)
48. S. Sudhakara, M. K. Ramanathi, C. Yarra, and P. K. Ghosh. 2019. An improved goodness of pronunciation (gop) measure for pronunciation evaluation with dnn-hmm system considering hmm transition probabilities. In Proc. Interspeech. [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%2E+2019%2E+An+improved+goodness+of+pronunciation+%28gop%29+measure+for+pronunciation+evaluation+with+dnn%2Dhmm+system+considering+hmm+transition+probabil)
49. Y. Sun, Y. Ming, X. Zhu, and Y. Li. 2022. Out-of-distribution detection with deep nearest neighbors. In Proc. ICML. [find](https://scholar.google.com/scholar?q=Y%2E+Sun%2C+Y%2E+Ming%2C+X%2E+Zhu%2C+and+Y%2E+Li%2E+2022%2E+Out%2Dof%2Ddistribution+detection+with+deep+nearest+neighbors%2E+In+Proc%2E+ICML%2E)
50. M. C. TA, T. Nagarajan, and P. Vijayalakshmi. 2016. Dysarthric speech corpus in tamil for rehabilitation research. In Proc. TENCON. [find](https://scholar.google.com/scholar?q=M%2E+C%2E+TA%2C+T%2E+Nagarajan%2C+and+P%2E+Vijayalakshmi%2E+2016%2E+Dysarthric+speech+corpus+in+tamil+for+rehabilitation+research%2E+In+Proc%2E+TENCON%2E)
51. William F Twaddell. 1952. Phonemes and allophones in speech analysis. Journal of the Acoustical Society of America. [find](https://scholar.google.com/scholar?q=William+F+Twaddell%2E+1952%2E+Phonemes+and+allophones+in+speech+analysis%2E+Journal+of+the+Acoustical+Society+of+America%2E)
52. A. Pasad, C-M. Chien, S. Settle, et al. 2024. [What Do Self-Supervised Speech Models Know About Words?](https://md.research.elamur.ai/free/en/papers/pasad-2024-what-do-self-supervised-speech/) TACL.
53. J. Vidal, L. Ferrer, and L. Brambilla. 2019. Epadb: A database for development of pronunciation assessment systems. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=J%2E+Vidal%2C+L%2E+Ferrer%2C+and+L%2E+Brambilla%2E+2019%2E+Epadb%3A+A+database+for+development+of+pronunciation+assessment+systems%2E+In+Proc%2E+Interspeech%2E)
54. A. Pasad, J-C Chou, and K. Livescu. 2021. Layer-wise analysis of a self-supervised speech representation model. In Proc. ASRU, pages 914–921. [find](https://scholar.google.com/scholar?q=A%2E+Pasad%2C+J%2DC+Chou%2C+and+K%2E+Livescu%2E+2021%2E+Layer%2Dwise+analysis+of+a+self%2Dsupervised+speech+representation+model%2E+In+Proc%2E+ASRU%2C+pages+914%E2%80%93921%2E)
55. Z. Wang, Q. Gu, Y. Ning, and H. Liu. 2015. High dimensional em algorithm: Statistical optimization and asymptotic normality. In Proc. NeurIPS. [find](https://scholar.google.com/scholar?q=Z%2E+Wang%2C+Q%2E+Gu%2C+Y%2E+Ning%2C+and+H%2E+Liu%2E+2015%2E+High+dimensional+em+algorithm%3A+Statistical+optimization+and+asymptotic+normality%2E+In+Proc%2E+NeurIPS%2E)
56. D. Wells, H. Tang, and K. Richmond. 2022. Phonetic Analysis of Self-supervised Representations of English Speech. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=D%2E+Wells%2C+H%2E+Tang%2C+and+K%2E+Richmond%2E+2022%2E+Phonetic+Analysis+of+Self%2Dsupervised+Representations+of+English+Speech%2E+In+Proc%2E+Interspeech%2E)
57. S. M. Witt and S. J. Young. 2000. Phone-level pronunciation scoring and assessment for interactive language learning. Speech Communication, 30:95–108. [find](https://scholar.google.com/scholar?q=S%2E+M%2E+Witt+and+S%2E+J%2E+Young%2E+2000%2E+Phone%2Dlevel+pronunciation+scoring+and+assessment+for+interactive+language+learning%2E+Speech+Communication%2C+30%3A95%E2%80%93108%2E)
58. X. Xu, Y. Kang, S. Cao, et al. 2021. Explore wav2vec 2.0 for Mispronunciation Detection. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=X%2E+Xu%2C+Y%2E+Kang%2C+S%2E+Cao%2C+et+al%2E+2021%2E+Explore+wav2vec+2%2E0+for+Mispronunciation+Detection%2E+In+Proc%2E+Interspeech%2E)
59. S-W. Yang, P-H. Chi, Y-S. Chuang, et al. 2021. SU-PERB: Speech Processing Universal PERformance Benchmark. In Proc. Interspeech, pages 1194–1198. [find](https://scholar.google.com/scholar?q=S%2DW%2E+Yang%2C+P%2DH%2E+Chi%2C+Y%2DS%2E+Chuang%2C+et+al%2E+2021%2E+SU%2DPERB%3A+Speech+Processing+Universal+PERformance+Benchmark%2E+In+Proc%2E+Interspeech%2C+pages+1194%E2%80%931198%2E)
60. E-J. Yeo, K. Choi, S. Kim, and M. Chung. 2023a. Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=E%2DJ%2E+Yeo%2C+K%2E+Choi%2C+S%2E+Kim%2C+and+M%2E+Chung%2E+2023a%2E+Speech+Intelligibility+Assessment+of+Dysarthric+Speech+by+using+Goodness+of+Pronunciation+with+Uncertainty+Quantification%2E+In+Proc%2E+Interspeech%2E)
61. E-J. Yeo, H. Ryu, J. Lee, et al. 2023b. Comparison of l2 korean pronunciation error patterns from five l1 backgrounds by using automatic phonetic transcription. In Proc. ICPhS. [find](https://scholar.google.com/scholar?q=E%2DJ%2E+Yeo%2C+H%2E+Ryu%2C+J%2E+Lee%2C+et+al%2E+2023b%2E+Comparison+of+l2+korean+pronunciation+error+patterns+from+five+l1+backgrounds+by+using+automatic+phonetic+transcription%2E+In+Proc%2E+ICPhS%2E)
62. S. J. Young, J. J. Odell, and P. C. Woodland. 1994. Tree-based state tying for high accuracy modelling. In Proc. HLT. [find](https://scholar.google.com/scholar?q=S%2E+J%2E+Young%2C+J%2E+J%2E+Odell%2C+and+P%2E+C%2E+Woodland%2E+1994%2E+Tree%2Dbased+state+tying+for+high+accuracy+modelling%2E+In+Proc%2E+HLT%2E)
63. J. Zhang, Z. Zhang, Y. Wang, et al. 2021. [speechocean762: An open-source non-native english speech corpus for pronunciation assessment](https://md.research.elamur.ai/free/en/papers/zhang-2021-speechocean762-open-source-non-native/). In Proc. Interspeech.
64. G. Zhao, S. Sonsaat, A. Silpachai, et al. 2018. L2-arctic: A non-native english speech corpus. In Proc. Interspeech. [find](https://scholar.google.com/scholar?q=G%2E+Zhao%2C+S%2E+Sonsaat%2C+A%2E+Silpachai%2C+et+al%2E+2018%2E+L2%2Darctic%3A+A+non%2Dnative+english+speech+corpus%2E+In+Proc%2E+Interspeech%2E)

*Updated 1 November 2026*