---
title: "Improved Mispronunciation detection system using a hybrid"
description: "The authors note that older approaches based on Goodness of Pronunciation (GOP) scores from GMM-HMM or DNN-HMM… 43 references."
authors: ["Neha Baranwal", "Sharatkumar Chilaka"]
year: 2022
venue: "arXiv:2201.10198"
source: "https://arxiv.org/abs/2201.10198"
doi: "10.48550/arxiv.2201.10198"
arxiv: "2201.10198"
licence: "CC0 1.0 (arXiv)"
licence_url: "http://creativecommons.org/publicdomain/zero/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/baranwal-2022-improved-mispronunciation-detection-system-using/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/baranwal-2022-improved-mispronunciation-detection-system-using/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/8/) / Improved Mispronunciation detection system using a hybrid CTC-ATT based approach for L2 English speakers

# Improved Mispronunciation detection system using a hybrid CTC-ATT based approach for L2 English speakers

**Authors:** Neha Baranwal and Sharatkumar Chilaka · **Year:** 2022 · **Venue:** arXiv:2201.10198 · **Licence:** [CC0 1.0 (arXiv)](http://creativecommons.org/publicdomain/zero/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2201.10198) · [PDF](https://arxiv.org/pdf/2201.10198) · [DOI 10.48550/arxiv.2201.10198](https://doi.org/10.48550/arxiv.2201.10198) · [arXiv 2201.10198](https://arxiv.org/abs/2201.10198) · [OpenAlex](https://openalex.org/W4221151498)

**Citations:** 2 citations (OpenAlex, 2026-10-14)

## Summary
The paper targets automatic mispronunciation detection for non-native (L2) adult learners of English. Mispronunciation detection is a core part of Computer Assisted Pronunciation Training (CAPT). The authors note that older approaches based on Goodness of Pronunciation (GOP) scores from GMM-HMM or DNN-HMM recognizers are complicated to build. They therefore study End-to-End (E2E) recognition-style detectors and compare three variants:

- a CNN-RNN-CTC baseline,
- the same model with a character-sequence attention decoder,
- the same model with a phoneme-based decoder.

The pipeline uses Kaldi-style data preparation on the L2-Arctic and TIMIT corpora, followed by fbank feature extraction, acoustic and language model training, and decoding. The authors frame errors mainly as phoneme substitutions, insertions and deletions, and they treat intelligibility, not native-likeness, as the goal. The study is limited to clean, read adult speech. The comparison is meant to show which E2E design, especially the hybrid CTC-attention one, gives a more efficient detector. The detailed result tables are not in the extracted text, so no figures are reported here.

## Key points
- Three compared systems: CNN-RNN-CTC, CNN-RNN-CTC with a character-based attention decoder, and CNN-RNN-CTC with a phoneme-based decoder.
- Data: L2-Arctic (non-native read English) and TIMIT. Kaldi is used to prepare the `text`, `wav.scp`, `utt2spk`, `spk2utt` and optional `segments` files, with sph2pipe/sox handling audio format conversion.
- Features: filter-bank (fbank) features were chosen over MFCC because they suit deep neural networks better.
- The literature review covers:
  - GOP (Witt and Young, 2000);
  - GMM-HMM and DNN-HMM GOP variants (Hu et al., 2015);
  - a DNN-HMM GOP that adds transition probabilities (Sudhakara et al., 2019);
  - hybrid CTC-Attention detectors (Lo et al., Yan et al., Zhang et al., 2020).
- Stated limitations: adult read speech only, studio-quality recordings, and no handling of background noise.

## Interesting ideas
- The cited anti-phone augmentation (Yan et al., 2020) randomly swaps reference labels for special "anti" labels, so the model learns what a wrong unit looks like without needing real error recordings.
- Errors are diagnosed as substitution, insertion or deletion against a reference sequence, which turns a vague notion of "wrong" into a small set of explainable edit types.
- Shorter units yield noisier judgements, since quality verdicts at phoneme level vary more than at word or phrase level, so evaluation granularity should be chosen deliberately.
- The training goal is intelligibility rather than sounding native, meaning success is defined by whether the listener understands, not by closeness to an ideal form.
- A hybrid CTC-attention model pairs an alignment-constrained objective with a free sequence decoder, so each part offsets the other's weaknesses.

## For Mova

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

- **I1** (learn): Corrupting a share of gold UD heads and labels into marked "anti" variants could supply cheap negative controls for training and testing the self-induced repair rules.
- **I2** (tokens): Comparing tokenizer and lemma output with gold through a typed edit alignment would make error reports explainable rather than reducing them to a single accuracy number.
- **I3** (learn): When witness parsers vote on silver data, agreement could be checked at both arc level and sentence/frame level, with less trust placed in isolated single-arc disagreements.
- **I4** (back): Generated text could be scored by whether the text → graph → text round trip preserves meaning, instead of by surface similarity to a reference sentence.
- **I5** (tree): gparse could pair a structurally constrained decoding check, such as a well-formed tree, with its free transformer scores, so that malformed outputs are caught and can be explained.

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

📚 Shelves (7): [🖥️ 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 · [🔊 Signal Processing](https://md.research.elamur.ai/free/en/shelves/computer-science/signal-processing/) · 452 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works

## Cite

Cite as: Neha Baranwal and Sharatkumar Chilaka. 2022. Improved Mispronunciation detection system using a hybrid CTC-ATT based approach for L2 English speakers. arXiv:2201.10198.

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

```bibtex
@misc{baranwal2022improved,
  title = {{Improved Mispronunciation detection system using a hybrid CTC-ATT based approach for L2 English speakers}},
  author = {Neha Baranwal and Sharatkumar Chilaka},
  year = {2022},
  doi = {10.48550/arxiv.2201.10198},
  eprint = {2201.10198},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2201.10198}
}
```

- [← previous How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection](https://md.research.elamur.ai/free/en/papers/ma-2022-how-do-we-get-there/)
- [next → Improving Dialogue Act Recognition with Augmented Data](https://md.research.elamur.ai/free/en/papers/mahajan-2022-improving-dialogue-act-recognition-augmented/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/8/)

## References

43 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Amodei, D., Anubhai, R., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Chen, J., Chrzanowski, M., Coates, A., Diamos, G., Elsen, E., Engel, J., Fan, L., Fougner, C., Han, T., Hannun, A., Jun, B., LeGresley, P., Lin, L., Narang, S., Ng, A., Ozair, S., Prenger, R., Raiman, J., Satheesh, S., Seetapun, D., Sengupta, S., Wang, Y., Wang, Z., Wang, C., Xiao, B., Yogatama, D., Zhan, J. and Zhu, Z., (2015) [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://md.research.elamur.ai/free/en/papers/amodei-2015-deep-speech-2-end-end/). 33rd International Conference on Machine Learning, ICML 2016, [online] 1, pp.312–321. Available at: http://arxiv.org/abs/1512.02595. [↗](https://arxiv.org/abs/1512.02595)
2. Bahdanau, D., Cho, K. and Bengio, Y., (2014) [Neural Machine Translation by Jointly Learning to Align and Translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, [online] pp.1–15. Available at: http://arxiv.org/abs/1409.0473. [↗](https://arxiv.org/abs/1409.0473)
3. Chauhan, P.M. and Desai, N.P., (2014) Mel Frequency Cepstral Coefficients (MFCC) based speaker identification in noisy environment using wiener filter. In: 2014 International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE). [online] IEEE, pp.1–5. Available at: [http://ieeexplore.ieee.org/document/6921394/](http://ieeexplore.ieee.org/document/6921394/). [↗](http://ieeexplore.ieee.org/document/6921394/)
4. Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K. and Bengio, Y., (2015) [Attention-Based Models for Speech Recognition](https://md.research.elamur.ai/free/en/papers/chorowski-2015-attention-based-models-speech-recognition/). In: Advances in Neural Information Processing Systems. [online] pp.577–585. Available at: http://arxiv.org/abs/1506.07503. [↗](https://arxiv.org/abs/1506.07503)
5. Feng, Y., Fu, G., Chen, Q. and Chen, K., (2020) SED-MDD: Towards Sentence Dependent End-To-End Mispronunciation Detection and Diagnosis. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2020-May, pp.3492–3496. [find](https://scholar.google.com/scholar?q=Feng%2C+Y%2E%2C+Fu%2C+G%2E%2C+Chen%2C+Q%2E+and+Chen%2C+K%2E%2C+%282020%29+SED%2DMDD%3A+Towards+Sentence+Dependent+End%2DTo%2DEnd+Mispronunciation+Detection+and+Diagnosis%2E+ICASSP%2C+IEEE+International+Conference+on+Acoustics%2C+Speech+and+)
6. Garofolo, J.S., Lamel, L.F., Fischer, W.M., Fiscus, J.G., Pallett, D.S. and Dahlgren, N.L., (1986) The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CD-ROM. Nist, [online] pp.1–94. Available at: [https://perso.limsi.fr/lamel/TIMIT_NISTIR4930.pdf%0Ahttp://scholar.google.com/scholar?hl=en&btnG=Search&q](https://perso.limsi.fr/lamel/TIMIT_NISTIR4930.pdf%0Ahttp://scholar.google.com/scholar?hl=en&btnG=Search&q) =intitle:Darpa+timit#7%0Ahttp://perso.limsi.fr/lamel/TIMIT_NISTIR4 50 930.pdf. [↗](https://perso.limsi.fr/lamel/TIMIT_NISTIR4930.pdf%0Ahttp://scholar.google.com/scholar?hl=en&btnG=Search&q)
7. Graves, A., Fernández, S., Gomez, F. and Schmidhuber, J., (2006) Connectionist temporal classification. In: Proceedings of the 23rd international conference on Machine learning - ICML ’06. [online] New York, New York, USA: ACM Press, pp.369–376. Available at: [http://portal.acm.org/citation.cfm?doid=1143844.1143891](http://portal.acm.org/citation.cfm?doid=1143844.1143891). [↗](http://portal.acm.org/citation.cfm?doid=1143844.1143891)
8. Hendrik Buschmeier, M.W., (2013) TextGridTools: A TextGrid Processing and Analysis Toolkit for Python. In: Tagungsband der 24. Konferenz zur Elektronischen Sprachsignalverarbeitung (ESSV 2013). pp.152–157. [find](https://scholar.google.com/scholar?q=Hendrik+Buschmeier%2C+M%2EW%2E%2C+%282013%29+TextGridTools%3A+A+TextGrid+Processing+and+Analysis+Toolkit+for+Python%2E+In%3A+Tagungsband+der+24%2E+Konferenz+zur+Elektronischen+Sprachsignalverarbeitung+%28ESSV+2013%29%2E+pp%2E152)
9. Hu, W., Qian, Y., Soong, F.K. and Wang, Y., (2015) Improved mispronunciation detection with deep neural network trained acoustic models and transfer learning based logistic regression classifiers. Speech Communication, [online] 67, pp.154–166. Available at: http://dx.doi.org/10.1016/j.specom.2014.12.008. [↗](https://doi.org/10.1016/j.specom.2014.12.008)
10. Kim, S., Hori, T. and Watanabe, S., (2017) Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [online] IEEE, pp.4835–4839. Available at: [http://ieeexplore.ieee.org/document/7953075/](http://ieeexplore.ieee.org/document/7953075/). [↗](http://ieeexplore.ieee.org/document/7953075/)
11. Kumar, Y. and Singh, N., (2019) A Comprehensive View of Automatic Speech Recognition System - A Systematic Literature Review. In: 2019 International Conference on Automation, Computational and Technology Management (ICACTM). [online] IEEE, pp.168–173. Available at: https://ieeexplore.ieee.org/document/8776714/. [↗](https://doi.org/10.1109/icactm.2019.8776714)
12. Leung, W.-K., Liu, X. and Meng, H., (2019) CNN-RNN-CTC Based End-to-end Mispronunciation Detection and Diagnosis. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [online] IEEE, pp.8132–8136. Available at: [https://ieeexplore.ieee.org/document/8682654/](https://ieeexplore.ieee.org/document/8682654/). [↗](https://ieeexplore.ieee.org/document/8682654/)
13. Li, K., Qian, X. and Meng, H., (2017) Mispronunciation Detection and Diagnosis in L2 English Speech Using Multidistribution Deep Neural Networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, [online] 251, pp.193–207. Available at:51 http://ieeexplore.ieee.org/document/7752846/. [↗](https://doi.org/10.1109/taslp.2016.2621675)
14. Li, W., Siniscalchi, S.M., Chen, N.F. and Lee, C.-H., (2016) Improving non-native mispronunciation detection and enriching diagnostic feedback with DNN-based speech attribute modeling. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [online] IEEE, pp.6135–6139. Available at: [http://ieeexplore.ieee.org/document/7472856/](http://ieeexplore.ieee.org/document/7472856/). [↗](http://ieeexplore.ieee.org/document/7472856/)
15. Lo, T.-H., Weng, S.-Y., Chang, H.-J. and Chen, B., (2020) An Effective End-to-End Modeling Approach for Mispronunciation Detection. In: Interspeech 2020. [online] ISCA: ISCA, pp.3027–3031. Available at: http://arxiv.org/abs/2005.08440. [↗](https://arxiv.org/abs/2005.08440)
16. Lo, W.K., Zhang, S. and Meng, H., (2010) Automatic derivation of phonological rules for mispronunciation detection in a Computer-Assisted Pronunciation Training System. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. pp.765–768. [find](https://scholar.google.com/scholar?q=Lo%2C+W%2EK%2E%2C+Zhang%2C+S%2E+and+Meng%2C+H%2E%2C+%282010%29+Automatic+derivation+of+phonological+rules+for+mispronunciation+detection+in+a+Computer%2DAssisted+Pronunciation+Training+System%2E+In%3A+Proceedings+of+the+11th+Ann)
17. Manjutha, M., Gracy, J., Subashini, P. and Krishnaveni, and M., (2017) Automated Speech Recognition System – A Literature Review. Computational Methods, Communication Techniques and Informatics, [online] 42, pp.205–212. Available at: [https://www.researchgate.net/profile/Kalaiselvi_Thiruvenkadam/publication/319077453_Computation_Methods_Co](https://www.researchgate.net/profile/Kalaiselvi_Thiruvenkadam/publication/319077453_Computation_Methods_Co) mmunication_Techniques_and_Informatics/links/5993f440aca272ec9087ac00/Computation-Methods-Communication-Techniques-and-Informatics.pdf#page=223. [↗](https://www.researchgate.net/profile/Kalaiselvi_Thiruvenkadam/publication/319077453_Computation_Methods_Co)
18. Povey, D., Ghoshal, A., Goel, N., Hannemann, M., Qian, Y., Schwarz, P., Silovsk, J. and Motl, P., (2011) The Kaldi Speech Recognition Toolkit. Canadian journal of occupational therapy. Revue canadienne d’ergotherapie. [online] Available at: [http://publications.idiap.ch/downloads/papers/2012/Povey_ASRU2011_2011.pdf](http://publications.idiap.ch/downloads/papers/2012/Povey_ASRU2011_2011.pdf). [↗](http://publications.idiap.ch/downloads/papers/2012/Povey_ASRU2011_2011.pdf)
19. Purwins, H., Li, B., Virtanen, T., Schluter, J., Chang, S.-Y. and Sainath, T., (2019) Deep Learning for Audio Signal Processing. IEEE Journal of Selected Topics in Signal Processing, [online] 132, pp.206–219. Available at: https://www.degruyter.com/document/doi/10.1515/9783110670905-006/html. 52 Qian, X., Soong, F. and Meng, H., (2010) Discriminative acoustic model for improving mispronunciation detection and diagnosis in computer-aided pronunciation training (CAPT). In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. pp.757–760. [↗](https://doi.org/10.1515/9783110670905-006/html)
20. Watanabe, S., Hori, T., Kim, S., Hershey, J.R. and Hayashi, T., (2017) Hybrid CTC/Attention Architecture for End-to-End Speech Recognition. IEEE Journal of Selected Topics in Signal Processing, [online] 118`, pp.1240–1253. Available at: http://www.ncbi.nlm.nih.gov/pubmed/20400762. [↗](https://doi.org/10.1109/jstsp.2017.2763455)
21. Witt, S.M., (2012) Automatic error detection in pronunciation training: Where we are and where we need to go. In: Proceedings of the International Symposium on Automatic Detection of Errors in Pronunciation Training (IS ADEPT). [online] pp.1–8. Available at: [http://www.researchgate.net/publication/250306074_Automatic_Error_Detection_in_Pronunciation_Training_Wher](http://www.researchgate.net/publication/250306074_Automatic_Error_Detection_in_Pronunciation_Training_Wher) e_we_are_and_where_we_need_to_go/file/9c960525580accbe92.pdf. [↗](http://www.researchgate.net/publication/250306074_Automatic_Error_Detection_in_Pronunciation_Training_Wher)
22. Witt, S.M. and Young, S.J., (2000) Phone-level pronunciation scoring and assessment for interactive language learning. Speech Communication, [online] 302, pp.95–108. Available at: http://svr-www.eng.cam.ac.uk/~sjy/papers/wiyo00.pdf. [↗](https://doi.org/10.1016/s0167-6393(99)00044-8)
23. Yan, B.-C., Wu, M.-C., Hung, H.-T. and Chen, B., (2020) [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: Interspeech 2020. [online] ISCA: ISCA, pp.3032–3036. Available at: [http://www.isca-speech.org/archive/Interspeech_2020/abstracts/1616.html](http://www.isca-speech.org/archive/Interspeech_2020/abstracts/1616.html). [↗](http://www.isca-speech.org/archive/Interspeech_2020/abstracts/1616.html)
24. Zhang, L., Zhao, Z., Ma, C., Shan, L., Sun, H., Jiang, L., Deng, S. and Gao, C., (2020) End-to-End Automatic Pronunciation Error Detection Based on Improved Hybrid CTC/Attention Architecture. Sensors, [online] 207, p.1809. Available at: https://www.mdpi.com/1424-8220/20/7/1809. [↗](https://doi.org/10.3390/s20071809)
25. Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Laurent, C., Bengio, Y. and Courville, A., (2016) Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. [online] pp.410–414. Available at: [http://www.isca-53](http://www.isca-53) speech.org/archive/Interspeech_2016/abstracts/1446.html. [↗](http://www.isca-53)
26. Zhao, G., Sonsaat, S., Silpachai, A., Lucic, I., Chukharev-Hudilainen, E., Levis, J. and Gutierrez-Osuna, R., (2018) L2-ARCTIC: A Non-native English Speech Corpus. In: Interspeech 2018. [online] ISCA: ISCA, pp.2783–2787. Available at: [http://www.isca-speech.org/archive/Interspeech_2018/abstracts/1110.html](http://www.isca-speech.org/archive/Interspeech_2018/abstracts/1110.html). [↗](http://www.isca-speech.org/archive/Interspeech_2018/abstracts/1110.html)
27. Microsoft Research (2017) Automatic Speech Recognition - An Overview [online video] Available at: [https://www.youtube.com/watch?v=q67z7PTGRi8&t=2192s](https://www.youtube.com/watch?v=q67z7PTGRi8&t=2192s) [Accessed: 9th June 2021] Wikipedia (2021) Spectrogram [online image] Available at: https://en.wikipedia.org/wiki/Spectrogram#/media/File:Spectrogram-19thC.png [Accessed: 07th June 2021] Wikimedia (2021) FFT-Time-Frequency-View [online image] Available at: https://commons.wikimedia.org/wiki/File:FFT-Time-Frequency-View.png [Accessed: 22nd March 2021] Wikipedia (2021) Audio bit depth [online image] Available at: https://en.wikipedia.org/wiki/Audio_bit_depth#/media/File:4-bit-linear-PCM.svg [Accessed: 22nd March 2021] [↗](https://www.youtube.com/watch?v=q67z7PTGRi8&t=2192s)
28. Springer, 2014. Conflict resolution in human-robot interaction. Neha Baranwal and Gora Chand Nandi. An efficient gesture based humanoid learning using wavelet descriptor and mfcc techniques. International Journal of Machine Learning and Cybernetics, 8(4):1369–1388, 2017. Neha Baranwal and Gora Chand Nandi. A mathematical framework for possibility theory-based hidden markov model. International Journal of Bio-Inspired Computation, 10(4):239–247, 2017. Neha Baranwal, Gora Chand Nandi, and Avinash Kumar Singh. Real-time gesture–based communication using possibility theory–based hidden markov model. Computational Intelligence, 33(4):843–862, 2017. Neha Baranwal, Avinash Kumar Singh, and Suna Bench. Extracting primary objects and spatial relations from sentences. In 11th International Conference on Agents and Artificial Intelligence, Prague, Czech Republic, 2019. Neha Baranwal, Avinash Kumar Singh, and Thomas Hellstrom. Fusion of gesture and speech for increased accuracy in human robot interaction. In 2019 24th International Conference on Methods and Models in Automation and Robotics (MMAR), pages 139–144. [find](https://scholar.google.com/scholar?q=Springer%2C+2014%2E+Conflict+resolution+in+human%2Drobot+interaction%2E+Neha+Baranwal+and+Gora+Chand+Nandi%2E+An+efficient+gesture+based+humanoid+learning+using+wavelet+descriptor+and+mfcc+techniques%2E+Internati)
29. IEEE, 2019. Neha Baranwal, Avinash Kumar Singh, and Gora Chand Nandi. Development of a framework for human– robot interactions with indian sign language using possibility theory. International Journal of Social Robotics, 9(4):563–574, 2017. Neha Baranwal, Neha Singh, and Gora Chand Nandi. Implementation of mfcc based hand gesture recognition on hoap-2 using webots platform. In 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pages 1897–1902. [find](https://scholar.google.com/scholar?q=IEEE%2C+2019%2E+Neha+Baranwal%2C+Avinash+Kumar+Singh%2C+and+Gora+Chand+Nandi%2E+Development+of+a+framework+for+human%E2%80%93+robot+interactions+with+indian+sign+language+using+possibility+theory%2E+International+Journal)
30. IEEE, 2014. Neha Baranwal, Kumud Tripathi, and GC Nandi. Possibility theory based continuous indian sign language gesture recognition. In TENCON 2015-2015 IEEE Region 10 Conference, pages 1–5. [find](https://scholar.google.com/scholar?q=IEEE%2C+2014%2E+Neha+Baranwal%2C+Kumud+Tripathi%2C+and+GC+Nandi%2E+Possibility+theory+based+continuous+indian+sign+language+gesture+recognition%2E+In+TENCON+2015%2D2015+IEEE+Region+10+Conference%2C+pages+1%E2%80%935%2E)
31. IEEE, 2015. 10. Neha Baranwal, Shweta Tripathi, and Gora Chand Nandi. A speaker invariant speech recognition technique using hfcc features in isolated hindi words. International Journal of Computational Intelligence Studies, 3(4):277–291, 2014. 11. Avinash Kumar Singh, Neha Baranwal, Kai-Florian Richter, Thomas Hellstrom, and Suna Bensch. Towards verbal explanations by collaborating robot teams. In International Conference on Social Robotics (ICSR19), Workshop Quality of Interaction in Socially Assistive Robots, Madrid, Spain, November 26-29, 2019., 2019. 12. Avinash Kumar Singh, Neha Baranwal, and Gora Chand Nandi. Human perception based criminal identification through human robot interaction. In 2015 Eighth International Conference on Contemporary Computing (IC3), pages 196–201. [find](https://scholar.google.com/scholar?q=IEEE%2C+2015%2E+10%2E+Neha+Baranwal%2C+Shweta+Tripathi%2C+and+Gora+Chand+Nandi%2E+A+speaker+invariant+speech+recognition+technique+using+hfcc+features+in+isolated+hindi+words%2E+International+Journal+of+Computation)
32. IEEE, 2015. 13. Avinash Kumar Singh, Neha Baranwal, and Gora Chand Nandi. Development of a self reliant humanoid robot for sketch drawing. Multimedia Tools and Applications, 76(18):18847–18870, 2017. 14. Avinash Kumar Singh, Neha Baranwal, and Gora Chand Nandi. A rough set based reasoning approach for criminal identification. International Journal of Machine Learning and Cybernetics, 10(3):413–431, 2019. 15. Avinash Kumar Singh, Neha Baranwal, and Kai-Florian Richter. An empirical review of calibration techniques for the pepper humanoid robots rgb and depth camera. In Proceedings of SAI Intelligent Systems Conference, pages 1026–1038. [find](https://scholar.google.com/scholar?q=IEEE%2C+2015%2E+13%2E+Avinash+Kumar+Singh%2C+Neha+Baranwal%2C+and+Gora+Chand+Nandi%2E+Development+of+a+self+reliant+humanoid+robot+for+sketch+drawing%2E+Multimedia+Tools+and+Applications%2C+76%2818%29%3A18847%E2%80%9318870%2C+2017%2E+)
33. Springer, 2019. 16. Avinash Kumar Singh, Pavan Chakraborty, and GC Nandi. Sketch drawing by nao humanoid robot. In TENCON 2015-2015 IEEE Region 10 Conference, pages 1–6. [find](https://scholar.google.com/scholar?q=Springer%2C+2019%2E+16%2E+Avinash+Kumar+Singh%2C+Pavan+Chakraborty%2C+and+GC+Nandi%2E+Sketch+drawing+by+nao+humanoid+robot%2E+In+TENCON+2015%2D2015+IEEE+Region+10+Conference%2C+pages+1%E2%80%936%2E)
34. IEEE, 2015. 17. Avinash Kumar Singh, Piyush Joshi, and Gora Chand Nandi. Face liveness detection through face structure analysis. International Journal of Applied Pattern Recognition, 1(4):338–360, 2014. 18. Avinash Kumar Singh, Piyush Joshi, and Gora Chand Nandi. Face recognition with liveness detection using eye and mouth movement. In 2014 International Conference on Signal Propagation and Computer Technology (ICSPCT 2014), pages 592–597. [find](https://scholar.google.com/scholar?q=IEEE%2C+2015%2E+17%2E+Avinash+Kumar+Singh%2C+Piyush+Joshi%2C+and+Gora+Chand+Nandi%2E+Face+liveness+detection+through+face+structure+analysis%2E+International+Journal+of+Applied+Pattern+Recognition%2C+1%284%29%3A338%E2%80%93360%2C+20)
35. IEEE, 2014. 19. Avinash Kumar Singh, Piyush Joshi, and Gora Chand Nandi. Development of a fuzzy expert system based liveliness detection scheme for biometric authentication. arXiv preprint arXiv:1609.05296, 2016. 20. Avinash Kumar Singh, Arun Kumar, GC Nandi, and Pavan Chakroborty. Expression invariant fragmented face recognition. In 2014 International Conference on Signal Propagation and Computer Technology (ICSPCT 2014), pages 184–189. [↗](https://arxiv.org/abs/1609.05296)
36. IEEE, 2014. 21. Avinash Kumar Singh and Gora Chand Nandi. Face recognition using facial symmetry. In Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology, pages 550–554. [find](https://scholar.google.com/scholar?q=IEEE%2C+2014%2E+21%2E+Avinash+Kumar+Singh+and+Gora+Chand+Nandi%2E+Face+recognition+using+facial+symmetry%2E+In+Proceedings+of+the+Second+International+Conference+on+Computational+Science%2C+Engineering+and+Inform)
37. ACM, 2012. 22. Avinash Kumar Singh and Gora Chand Nandi. Nao humanoid robot: Analysis of calibration techniques for robot sketch drawing. Robotics and Autonomous Systems, 79:108–121, 2016. 23. Avinash Kumar Singh and Gora Chand Nandi. Visual perception-based criminal identification: a query-based approach. Journal of Experimental & Theoretical Artificial Intelligence, 29(1):175–196, 2017. 24. Neha Singh, Neha Baranwal, and GC Nandi. Implementation and evaluation of dwt and mfcc based isl gesture recognition. In 2014 9th International Conference on Industrial and Information Systems (ICIIS), pages 1–7. [find](https://scholar.google.com/scholar?q=ACM%2C+2012%2E+22%2E+Avinash+Kumar+Singh+and+Gora+Chand+Nandi%2E+Nao+humanoid+robot%3A+Analysis+of+calibration+techniques+for+robot+sketch+drawing%2E+Robotics+and+Autonomous+Systems%2C+79%3A108%E2%80%93121%2C+2016%2E+23%2E+Avinash)
38. IEEE, 2014. 25. Kumud Tripathi, Neha Baranwal, and Gora Chand Nandi. Continuous dynamic Indian sign language gesture recognition with invariant backgrounds. In 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pages 2211–2216. [find](https://scholar.google.com/scholar?q=IEEE%2C+2014%2E+25%2E+Kumud+Tripathi%2C+Neha+Baranwal%2C+and+Gora+Chand+Nandi%2E+Continuous+dynamic+Indian+sign+language+gesture+recognition+with+invariant+backgrounds%2E+In+2015+International+Conference+on+Advance)
39. IEEE, 2015. 26. Shweta Tripathy, Neha Baranwal, and GC Nandi. A mfcc based hindi speech recognition technique using htk toolkit. In 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013), pages 539–544. [find](https://scholar.google.com/scholar?q=IEEE%2C+2015%2E+26%2E+Shweta+Tripathy%2C+Neha+Baranwal%2C+and+GC+Nandi%2E+A+mfcc+based+hindi+speech+recognition+technique+using+htk+toolkit%2E+In+2013+IEEE+Second+International+Conference+on+Image+Information+Proce)
40. IEEE, 2013. 27. Singh, Avinash Kumar, Baranwal, Neha, Richter, Kai-Florian, Hellström, Thomas and Bensch, Suna. "Verbal explanations by collaborating robot teams" Paladyn, Journal of Behavioral Robotics, vol. 12, no. 1, 2021, pp. 47-57. 28. [find](https://scholar.google.com/scholar?q=IEEE%2C+2013%2E+27%2E+Singh%2C+Avinash+Kumar%2C+Baranwal%2C+Neha%2C+Richter%2C+Kai%2DFlorian%2C+Hellstr%C3%B6m%2C+Thomas+and+Bensch%2C+Suna%2E+%22Verbal+explanations+by+collaborating+robot+teams%22+Paladyn%2C+Journal+of+Behavioral+Roboti)
41. Singh A.K., Baranwal N., Richter KF., Hellström T., Bensch S. (2020) Understandable Collaborating Robot Teams. In: De La Prieta F. et al. (eds) Highlights in Practical Applications of Agents, Multi-Agent Systems, and Trust-worthiness. The PAAMS Collection. PAAMS 2020. Communications in Computer and Information Science, vol 1233. Springer 29. [find](https://scholar.google.com/scholar?q=Singh+A%2EK%2E%2C+Baranwal+N%2E%2C+Richter+KF%2E%2C+Hellstr%C3%B6m+T%2E%2C+Bensch+S%2E+%282020%29+Understandable+Collaborating+Robot+Teams%2E+In%3A+De+La+Prieta+F%2E+et+al%2E+%28eds%29+Highlights+in+Practical+Applications+of+Agents%2C+Multi%2DAg)
42. Singh A.K., Baranwal N., Richter KF., Hellström T., Bensch S. (2020) Understandable Teams of Pepper Robots. In: Demazeau Y., Holvoet T., Corchado J., Costantini S. (eds) Advances in Practical Applications of Agents, Multi-Agent Systems, and Trustworthiness. The PAAMS Collection. PAAMS 2020. Lecture Notes in Computer Science, vol 12092. Springer. 30. Singh, Avinash, Neha Baranwal, and Kai-Florian Richter. "A Fuzzy Inference System for a Visually Grounded Robot State of Mind." 24th European Conference on Artificial Intelligence (ECAI 2020), Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), Virtual, August 29-September 8, 2020. [find](https://scholar.google.com/scholar?q=Singh+A%2EK%2E%2C+Baranwal+N%2E%2C+Richter+KF%2E%2C+Hellstr%C3%B6m+T%2E%2C+Bensch+S%2E+%282020%29+Understandable+Teams+of+Pepper+Robots%2E+In%3A+Demazeau+Y%2E%2C+Holvoet+T%2E%2C+Corchado+J%2E%2C+Costantini+S%2E+%28eds%29+Advances+in+Practical+Applicat)
43. IOS Press, 2020. 31. Baranwal, Neha, and Kamalika Dutta. "Peak detection based spread spectrum Audio Watermarking using discrete Wavelet Transform." International Journal of Computer Applications 24.1 (2011): 16-20. 32. Gadanayak, Bismita, Chittaranjan Pradhan, and Neha Baranwal. "Secured partial MP3 encryption technique." International Journal of Computer Science and Information Technologies 2.4 (2011): 1584-1587. 33. Baranwal, Neha, and Kamalika Datta. "Comparative study of spread spectrum based audio watermarking techniques." 2011 International Conference on Recent Trends in Information Technology (ICRTIT). [find](https://scholar.google.com/scholar?q=IOS+Press%2C+2020%2E+31%2E+Baranwal%2C+Neha%2C+and+Kamalika+Dutta%2E+%22Peak+detection+based+spread+spectrum+Audio+Watermarking+using+discrete+Wavelet+Transform%2E%22+International+Journal+of+Computer+Applications+24%2E1)

*Updated 1 November 2026*