Implementing type-2 fuzzy logic for post-ASR correction in low-resource languages: A case study in Sundanese

Authors

https://doi.org/10.48313/uda.v2i3.73

Abstract

Low-resource languages like Sundanese continue to challenge Automatic Speech Recognition (ASR) systems owing to dialectal variation, limited data, and phonetic variance, which lower transcription quality. This research proposes a type-2 fuzzy logic-based post-processing system to increase transcription accuracy in such cases. First, we transcribe using Whisper, a cutting-edge multilingual ASR model. These outputs are improved by fuzzy language rules based on regular Sundanese phonological and morphological faults. In particular, our technique addresses ASR ambiguity for Sundanese words with complicated meanings, consonant alterations, and reduplications. Interval-valued membership functions let the type-2 fuzzy system turn approximation or uncertain phrases into more correct linguistic ones. The recommended correction approach decreases Word Error Rate (WER) by 25% on average in 30 typical samples using a publicly accessible Sundanese speech dataset. This method is unique in its interpretable and rule-extendable design.  It's ideal for underrepresented languages, unlike post-editing or statistical adjustments. This work supports language inclusion in speech technologies by showing how fuzzy logic in the ASR pipeline may enhance transcription quality in circumstances with little linguistic data, and promotes speech technology linguistic inclusion.     

Keywords:

Type-2 fuzzy logic, Automatic speech recognition, Low-resource languages, Sundanese language, Post-processing correction

References

  1. [1] Mittal, K., Jain, A., Vaisla, K. S., Castillo, O., & Kacprzyk, J. (2020). A comprehensive review on type 2 fuzzy logic applications: Past, present and future. Engineering applications of artificial intelligence, 95, 103916. https://doi.org/10.1016/j.engappai.2020.103916
  2. [2] Zadeh, L. A. (1965). Fuzzy sets. Information and control, 8(3), 338–353. https://doi.org/10.1016/S0019-9958(65)90241-X
  3. [3] Zhang, Z., Yu, W., Martínez, L., & Gao, Y. (2019). Managing multigranular unbalanced hesitant fuzzy linguistic information in multiattribute large-scale group decision making: A linguistic distribution-based approach. IEEE transactions on fuzzy systems, 28(11), 2875–2889. https://doi.org/10.1109/TFUZZ.2019.2949758
  4. [4] Haghrah, A. A., Ghaemi, S., & Badamchizadeh, M. A. (2025). PyIT2FLS: An open-source Python framework for flexible and scalable development of type 1 and interval type 2 fuzzy logic models. SoftwareX, 30, 102146. https://doi.org/10.1016/j.softx.2025.102146
  5. [5] Hidalgo, D., Castillo, O., & Melin, P. (2009). Type-1 and type-2 fuzzy inference systems as integration methods in modular neural networks for multimodal biometry and its optimization with genetic algorithms. Information sciences, 179(13), 2123–2145. https://doi.org/10.1016/j.ins.2008.07.013
  6. [6] Maji, S., Maity, S., Giri, D., Nielsen, I., & Maiti, M. (2025). Multi-objective multi-path COVID-19 medical waste collection problem with type-2 fuzzy logic based risk using partial opposition-based weighted genetic algorithm. Engineering applications of artificial intelligence, 143, 109916. https://doi.org/10.1016/j.engappai.2024.109916
  7. [7] Pugalenthi, R., Oliver, A. S., & Anuradha, M. (2020). Impulse noise reduction using hybrid neuro-fuzzy filter with improved firefly algorithm from X-ray bio-images. International journal of imaging systems and technology, 30(4), 1119–1131. https://doi.org/10.1002/ima.22453
  8. [8] Akram, M., Naz, S., & Abbas, T. (2023). Complex q-rung orthopair fuzzy 2-tuple linguistic group decision-making framework with Muirhead mean operators. Artificial intelligence review, 56(9), 10227–10274. https://doi.org/10.1007/s10462-023-10408-4
  9. [9] Xiao, B., Lam, H. K., Yu, Y., & Li, Y. (2019). Sampled-data output-feedback tracking control for interval type-2 polynomial fuzzy systems. IEEE transactions on fuzzy systems, 28(3), 424–433. https://doi.org/10.1109/TFUZZ.2019.2907503
  10. [10] Martínez, R., Castillo, O., & Aguilar, L. T. (2009). Optimization of interval type-2 fuzzy logic controllers for a perturbed autonomous wheeled mobile robot using genetic algorithms. Information sciences, 179(13), 2158–2174. https://doi.org/10.1016/j.ins.2008.12.028
  11. [11] Boudia, A., Messalti, S., Zeghlache, S., & Harrag, A. (2025). Type-2 fuzzy logic controller-based maximum power point tracking for photovoltaic system. Electrical engineering & electromechanics, (1), 16–22. https://doi.org/10.20998/2074-272X.2025.1.03
  12. [12] Ontiveros, E., Melin, P., & Castillo, O. (2020). Comparative study of interval type-2 and general type-2 fuzzy systems in medical diagnosis. Information sciences, 525, 37–53. https://doi.org/10.1016/j.ins.2020.03.059
  13. [13] Belhadj, S. M., Meliani, B., Benbouhenni, H., Zaidi, S., Elbarbary, Z. M. S., & Alammer, M. M. (2025). Control of multi-level quadratic DC-DC boost converter for photovoltaic systems using type-2 fuzzy logic technique-based MPPT approaches. Heliyon. https://www.cell.com/heliyon/fulltext/S2405-8440(25)00561-4
  14. [14] Liang, Q., & Mendel, J. M. (2000). Interval type-2 fuzzy logic systems: theory and design. IEEE transactions on fuzzy systems, 8(5), 535–550. https://doi.org/10.1109/91.873577
  15. [15] Zhang, X., Wang, H., Stojanovic, V., Cheng, P., He, S., Luan, X., & Liu, F. (2022). Asynchronous fault detection for interval type-2 fuzzy nonhomogeneous higher level markov jump systems with uncertain transition probabilities. IEEE transactions on fuzzy systems, 30(7), 2487–2499. https://doi.org/10.1109/TFUZZ.2021.3086224
  16. [16] He, S., Wang, B., & Chen, Y. (2025). Improved optimal torque control for large scale floating offshore wind turbines based on interval type-2 fuzzy logic system. Ocean engineering, 330, 121186. https://doi.org/10.1016/j.oceaneng.2025.121186
  17. [17] Sharma, S., & Obaid, A. J. (2020). Mathematical modelling, analysis and design of fuzzy logic controller for the control of ventilation systems using MATLAB fuzzy logic toolbox. Journal of interdisciplinary mathematics, 23(4), 843–849. https://doi.org/10.1080/09720502.2020.1727611
  18. [18] Aliev, R. A., Pedrycz, W., Guirimov, B. G., Aliev, R. R., Ilhan, U., Babagil, M., & Mammadli, S. (2011). Type-2 fuzzy neural networks with fuzzy clustering and differential evolution optimization. Information sciences, 181(9), 1591–1608. https://doi.org/10.1016/j.ins.2010.12.014
  19. [19] Castillo, O., Cervantes, L., Soria, J., Sanchez, M., & Castro, J. R. (2016). A generalized type-2 fuzzy granular approach with applications to aerospace. Information sciences, 354, 165–177. https://doi.org/10.1016/j.ins.2016.03.001
  20. [20] Maroua, B., Laid, Z., Benbouhenni, H., Elbarbary, Z. M. S., Colak, I., & Alammer, M. M. (2025). Genetic algorithm type 2 fuzzy logic controller of microgrid system with a fractional-order technique. Scientific reports, 15(1), 6318. https://doi.org/10.1038/s41598-025-90239-1
  21. [21] Tolga, A. C., Parlak, I. B., & Castillo, O. (2020). Finite-interval-valued Type-2 Gaussian fuzzy numbers applied to fuzzy TODIM in a healthcare problem. Engineering applications of artificial intelligence, 87, 103352. https://doi.org/10.1016/j.engappai.2019.103352
  22. [22] Castro, J. R., Castillo, O., Melin, P., & Rodríguez-Díaz, A. (2009). A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks. Information sciences, 179(13), 2175–2193. https://doi.org/10.1016/j.ins.2008.10.016
  23. [23] Ambareesh, S., Chavan, P., Supreeth, S., Nandalike, R., Dayananda, P., & Rohith, S. (2025). A secure and energy-efficient routing using coupled ensemble selection approach and optimal type-2 fuzzy logic in WSN. Scientific reports, 15(1), 38. https://doi.org/10.1038/s41598-024-82635-w
  24. [24] Lim, C. K., & Chan, C. S. (2013, July). An inference engine based on Interval Type-2 Fuzzy BK subproduct. 2013 IEEE international conference on fuzzy systems (FUZZ-IEEE) (pp. 1-8). IEEE. https://doi.org/10.1109/FUZZ-IEEE.2013.6622368
  25. [25] Štěpnička, M., & Jayaram, B. (2010). On the suitability of the Bandler-Kohout subproduct as an inference mechanism. IEEE transactions on fuzzy systems, 18(2), 285–298. https://doi.org/10.1109/TFUZZ.2010.2041007
  26. [26] Chen, M. Y., & Linkens, D. A. (2004). Rule-base self-generation and simplification for data-driven fuzzy models. Fuzzy sets and systems, 142(2), 243–265. https://doi.org/10.1016/S0165-0114(03)00160-X

Downloads

Published

2025-09-11

Issue

Vol. 2 No. 3 (2025): Uncertainty Discourse and Applications

Section

Articles

How to Cite

Anshor, A. H., & Wiyatno, T. N. (2025). Implementing type-2 fuzzy logic for post-ASR correction in low-resource languages: A case study in Sundanese. Uncertainty Discourse and Applications, 2(3), 196-204. https://doi.org/10.48313/uda.v2i3.73

Similar Articles

31-39 of 39

You may also start an advanced similarity search for this article.