[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/langstream-2024-nazari-nolor-asr-based-framework-expedited/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/) / NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study

# NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study

**Authors:** Matthew Nazari · **Year:** 2024 · **Venue:** arXiv:2412.04717 **Link:** [arxiv.org/abs/2412.04717](https://arxiv.org/abs/2412.04717) · library `langstream-2024-nazari-nolor-asr-based-framework-expedited` · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) (arXiv)

[**0** citations](https://openalex.org/works?filter=cites:W4405173300) openalex · 2026-10-18[arXiv:2412.04717](https://openalex.org/S4306400194)[licence](http://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://arxiv.org/abs/2412.04717)
- [PDF](https://arxiv.org/pdf/2412.04717)
- [arXiv 2412.04717](https://arxiv.org/abs/2412.04717)
- [OpenAlex](https://openalex.org/W4405173300)

**Authors (1)**

1. [Matthew Nazari](https://openalex.org/A5102523470) h 0 · 0 citations · 2 works

Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart.

## What it is about

NoLoR is a four-step loop for documenting an unwritten or under-documented language: define a phonemic orthography, build a small initial dataset of transcribed speech, fine-tune a pretrained speech model, and then expand the dataset with the model's drafts, which people correct. The case is the Neo-Aramaic dialect of Urmi, with a 35-minute labelled set cut into about 600 clips of at most 15 seconds, and a wav2vec 2.0 checkpoint first fine-tuned on Persian. The model reaches a character error rate of 12.5 per cent on the test data. With the draft, transcription is 2.0 times faster for 15-second clips and up to 6.3 times faster for 5-minute clips. A subword tokenizer with a small vocabulary did worse than characters on so little text, and the single-speaker data was augmented for speed, pitch and microphone clarity.

## Ideas

- I1. Time the correction of a parser draft against writing the tree from scratch, on items of growing length, and report the speed-up in the same form as the paper's table. For Mova the draft comes from `gparse` over `treebanks/hbo/ptnk`, and the timing is run twice to check it is stable.
- I2. Two spellings for one language: a phonemic working orthography for the data, and a simplified keyboard spelling for readers (the paper writes a sh sound as the English digraph). Use the same split for an Aramaic variety, with the phonemic form as the master and the simple form as a display layer.
- I3. Small data favours tables over learned subwords. The paper found that a 256 or 512 subword vocabulary failed on a little text. For the `tools/hbo` segmenter, which uses learned prefix and suffix tables, compare it against a subword split on the held-out PTNK sentences and keep whichever is better on the small slice.

## For Mova

I1 goes into `treebanks/hbo/ptnk` as a correction-time measure for `gparse` drafts. I2 goes into [Script and phonology](https://md.mova.elamur.ai/free/en/docs/languages/arc/script-phonology/), with the simplified layer noted for `languages/jpa/`. I3 goes into `tools/hbo`, in the segmenter comparison.

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [arXiv 2412.04717](https://arxiv.org/abs/2412.04717)

```
@misc{nazari2024nolor,
  title = {{NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study}},
  author = {Nazari, Matthew},
  year = {2024},
  eprint = {2412.04717},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.04717}
}
```

- [← previous Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2024-majeed-ancient-but-digitized-developing-handwritten/)
- [next → Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learning](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2026-sliwa-machine-translation-between-english-syriac/)
- [↑ back to Aramaic](https://md.mova.elamur.ai/free/en/docs/papers/arc/)

## References

26 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adams, O.; Makarucha, A.; Neubig, G.; Bird, S.; and Cohn, T. 2017. Cross-Lingual Word Embeddings for Low-Resource Language Modeling. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, 937– 947. Valencia, Spain: Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/e17-1088)
2. Ardila, R.; Branson, M.; Davis, K.; Henretty, M.; Kohler, M.; Meyer, J.; Morais, R.; Saunders, L.; Tyers, F. M.; and Weber, G. 2019. Common Voice: A Massively-Multilingual Speech Corpus. arXiv. [find](https://scholar.google.com/scholar?q=Ardila%2C+R%2E%3B+Branson%2C+M%2E%3B+Davis%2C+K%2E%3B+Henretty%2C+M%2E%3B+Kohler%2C+M%2E%3B+Meyer%2C+J%2E%3B+Morais%2C+R%2E%3B+Saunders%2C+L%2E%3B+Tyers%2C+F%2E+M%2E%3B+and+Weber%2C+G%2E+2019%2E+Common+Voice%3A+A+Massively%2DMultilingual+Speech+Corpus%2E+arXiv%2E)
3. Baevski, A.; Zhou, H.; Mohamed, A.; and Auli, M. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. Bosch, L. t. 2000. Emotions: what is possible in the ASR framework. In ISCA Tutorial and Research Workshop (ITRW) on Speech and Emotion. [find](https://scholar.google.com/scholar?q=Baevski%2C+A%2E%3B+Zhou%2C+H%2E%3B+Mohamed%2C+A%2E%3B+and+Auli%2C+M%2E+2020%2E+wav2vec+2%2E0%3A+A+Framework+for+Self%2DSupervised+Learning+of+Speech+Representations%2E+Bosch%2C+L%2E+t%2E+2000%2E+Emotions%3A+what+is+possible+in+the+ASR+framewo)
4. Cahill, M.; and Karan, E. 2008. Factors in designing effective orthographies for unwritten languages. SIL International. [find](https://scholar.google.com/scholar?q=Cahill%2C+M%2E%3B+and+Karan%2C+E%2E+2008%2E+Factors+in+designing+effective+orthographies+for+unwritten+languages%2E+SIL+International%2E)
5. Chen, L.-W.; and Rudnicky, A. 2021. Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition. arXiv preprint arXiv:2110.06309. [↗](https://arxiv.org/abs/2110.06309)
6. Feng, S.; Żelasko, P.; Moro-Velázquez, L.; Abavisani, A.; Hasegawa-Johnson, M.; Scharenborg, O.; and Dehak, N. 2021a. How Phonotactics Affect Multilingual and Zero-Shot ASR Performance. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7238–7242. [↗](https://doi.org/10.1109/icassp39728.2021.9414478)
7. Feng, S. Y.; Gangal, V.; Wei, J.; Chandar, S.; Vosoughi, S.; Mitamura, T.; and Hovy, E. 2021b. A Survey of Data Augmentation Approaches for NLP. [↗](https://doi.org/10.18653/v1/2021.findings-acl.84)
8. Gaunt, D. 2020. The Long Assyrian Genocide. Collective and State Violence in Turkey, 56–96. [↗](https://doi.org/10.2307/j.ctv29sfvw6.6)
9. Graves, A. 2012. Connectionist Temporal Classification. Berlin, Heidelberg: Springer Berlin Heidelberg. ISBN 978-3-642-24797-2. [find](https://scholar.google.com/scholar?q=Graves%2C+A%2E+2012%2E+Connectionist+Temporal+Classification%2E+Berlin%2C+Heidelberg%3A+Springer+Berlin+Heidelberg%2E+ISBN+978%2D3%2D642%2D24797%2D2%2E)
10. Hedderich, M. A.; Lange, L.; Adel, H.; Strötgen, J.; and Klakow, D. 2020. A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios. [↗](https://doi.org/10.18653/v1/2021.naacl-main.201)
11. Khan, G. 2016. The Neo-Aramaic Dialect of the Assyrian Christians of Urmi (4 vols). Brill. [↗](https://doi.org/10.1163/9789004313934)
12. Khare, S.; Mittal, A. R.; Diwan, A.; Sarawagi, S.; Jyothi, P.; and Bharadwaj, S. 2021. Low Resource ASR: The Surprising Effectiveness of High Resource Transliteration. In Interspeech, 1529–1533. [↗](https://doi.org/10.21437/interspeech.2021-2062)
13. Malik, M.; Malik, M. K.; Mehmood, K.; and Makhdoom, I. 2021. Automatic speech recognition: a survey. Multimedia Tools and Applications, 80(6): 9411–9457. [↗](https://doi.org/10.1007/s11042-020-10073-7)
14. Moseley, C.; and Nicolas, A. 2010. Atlas of the world’s languages in Danger. UNESCO Pub. [find](https://scholar.google.com/scholar?q=Moseley%2C+C%2E%3B+and+Nicolas%2C+A%2E+2010%2E+Atlas+of+the+world%E2%80%99s+languages+in+Danger%2E+UNESCO+Pub%2E)
15. Neyshabur, B.; Bhojanapalli, S.; McAllester, D.; and Srebro, N. 2017. Exploring generalization in deep learning. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Neyshabur%2C+B%2E%3B+Bhojanapalli%2C+S%2E%3B+McAllester%2C+D%2E%3B+and+Srebro%2C+N%2E+2017%2E+Exploring+generalization+in+deep+learning%2E+Advances+in+neural+information+processing+systems%2C+30%2E)
16. NLLB Team; Costa-jussà, M. R.; Cross, J.; Çelebi, O.; Elbayad, M.; Heafield, K.; Heffernan, K.; Kalbassi, E.; Lam, J.; Licht, D.; Maillard, J.; Sun, A.; Wang, S.; Wenzek, G.; Youngblood, A.; Akula, B.; Barrault, L.; Gonzalez, G. M.; Hansanti, P.; Hoffman, J.; Jarrett, S.; Sadagopan, K. R.; Rowe, D.; Spruit, S.; Tran, C.; Andrews, P.; Ayan, N. F.; Bhosale, S.; Edunov, S.; Fan, A.; Gao, C.; Goswami, V.; Guzmán, F.; Koehn, P.; Mourachko, A.; Ropers, C.; Saleem, S.; Schwenk, H.; and Wang, J. 2022. No Language Left Behind: Scaling Human-Centered Machine Translation. [find](https://scholar.google.com/scholar?q=NLLB+Team%3B+Costa%2Djussa%CC%80%2C+M%2E+R%2E%3B+Cross%2C+J%2E%3B+C%CC%A7elebi%2C+O%2E%3B+Elbayad%2C+M%2E%3B+Heafield%2C+K%2E%3B+Heffernan%2C+K%2E%3B+Kalbassi%2C+E%2E%3B+Lam%2C+J%2E%3B+Licht%2C+D%2E%3B+Maillard%2C+J%2E%3B+Sun%2C+A%2E%3B+Wang%2C+S%2E%3B+Wenzek%2C+G%2E%3B+Youngblood%2C+A%2E%3B+Akula%2C+)
17. Omer, M. 2022. Religious Freedom in Iraq in 2021. [find](https://scholar.google.com/scholar?q=Omer%2C+M%2E+2022%2E+Religious+Freedom+in+Iraq+in+2021%2E)
18. Pike, K. L. 1971. Phonemics: A technique for reducing languages to writing. [find](https://scholar.google.com/scholar?q=Pike%2C+K%2E+L%2E+1971%2E+Phonemics%3A+A+technique+for+reducing+languages+to+writing%2E)
19. Ranathunga, S.; Lee, E.-S. A.; Skenduli, M. P.; Shekhar, R.; Alam, M.; and Kaur, R. 2021. Neural Machine Translation for Low-Resource Languages: A Survey. [find](https://scholar.google.com/scholar?q=Ranathunga%2C+S%2E%3B+Lee%2C+E%2E%2DS%2E+A%2E%3B+Skenduli%2C+M%2E+P%2E%3B+Shekhar%2C+R%2E%3B+Alam%2C+M%2E%3B+and+Kaur%2C+R%2E+2021%2E+Neural+Machine+Translation+for+Low%2DResource+Languages%3A+A+Survey%2E)
20. Shi, J.; Amith, J. D.; Garcı́a, R. C.; Sierra, E. G.; Duh, K.; and Watanabe, S. 2021. Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yoloxóchitl Mixtec. [↗](https://doi.org/10.18653/v1/2021.eacl-main.96)
21. SIL International. 2007. FLEx. [find](https://scholar.google.com/scholar?q=SIL+International%2E+2007%2E+FLEx%2E)
22. SIL International. 2010. SayMore. [find](https://scholar.google.com/scholar?q=SIL+International%2E+2010%2E+SayMore%2E)
23. Venezky, R. L. 2004. In search of the perfect orthography. Written Language & Literacy, 7(2): 139–163. [↗](https://doi.org/10.1075/wll.7.2.02ven)
24. Vicsi, K.; and Szaszák, G. 2006. Prosodic cues for automatic phrase boundary detection in ASR. In International Conference on Text, Speech and Dialogue, 547–554. Springer. [↗](https://doi.org/10.1007/11846406_69)
25. Xu, J.; Tan, X.; Ren, Y.; Qin, T.; Li, J.; Zhao, S.; and Liu, T.-Y. 2020. LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition. [↗](https://doi.org/10.1145/3394486.3403331)
26. Zahrer, A.; Zgank, A.; and Schuppler, B. 2020. Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu. In Proceedings of the Twelfth Language Resources and Evaluation Conference, 2893–2900. Marseille, France: European Language Resources Association. ISBN 979-10-95546-34-4. [find](https://scholar.google.com/scholar?q=Zahrer%2C+A%2E%3B+Zgank%2C+A%2E%3B+and+Schuppler%2C+B%2E+2020%2E+Towards+Building+an+Automatic+Transcription+System+for+Language+Documentation%3A+Experiences+from+Muyu%2E+In+Proceedings+of+the+Twelfth+Language+Resources+an)