SIMO: An Automatic Speech Recognition System for Paperless Manufactures

Abstract:

Despite environmental general conscience, heavy use of paper is still one fact in nowadays factories. The shorter the manufacturing production, the greater the tendency to employ paper to support quality tracking of pieces; using it to register measurements or nonconformities. This tendency increases drastically in some manufactures like aerospace, where typical production ratios vary between 9 and 18 subassemblies per month. The current work presents an automatic speech recognition system, meant to replace paper by a digitalized version of the manual writing task. The work presents (i) industrial use cases with benefits and requirements; (ii) the system architecture, including several tested free Automatic Speech Recognition modules, their analysis; and (iii) some open-source supporting modules that improves its functionality. The work concludes presenting several tests, showing the system performance against different kind of industrial noises, low to high quality microphones and users with different dialects.

• Periodical: Advances in Science and Technology (Volume 132)
• Pages: 129-139
• DOI: https://doi.org/10.4028/p-ZsZk7v
• Online since: October 2023
• Authors: Rafael Luque*, Adrián R. Galisteo, Paloma Vega, Eduardo Ferrera
• Keywords: Aerospace, Deep Learning, Paperless, Speech Recognition

References

[1] Djassemi, M., and Sena, J. A. (2006). "The paperless Factory: A review of issues and technologies." International Journal of Computer Science and Network Security, 6(12), 185.

[2] Hawley, J., and Mackowiak, B. (1991). "Paperless assembly using touchscreen based graphics." Eleventh IEEE/CHMT IEMT Symposium, pp.231-234, IEEE.

DOI: 10.1109/iemt.1991.279784

[3] Price, Tom, et al. (2012). "Paperless Track Inspection Record Keeping and Compliance." Rail Transportation Division Conference. Vol. 45073. American Society of Mechanical Engineers.

DOI: 10.1115/rtdf2012-9432

[4] Zakoldaev, D. A., A. V. Shukalov, and I. O. Zharinov. (2019). "From Industry 3.0 to Industry 4.0: production modernization and creation of innovative digital companies." IOP conference series: Materials Science and Engineering. Vol. 560. No. 1. IOP Publishing.

DOI: 10.1088/1757-899x/560/1/012206

[5] Helmke, H., et al. (2017). "Increasing atm efficiency with assistant based speech recognition." Proc. of the 13th USA/Europe Air Traffic Management Research and Development Seminar.

[6] Beato, B., et al. (2011). "Going paperless: implementing an electronic laboratory notebook in a bioanalytical laboratory." Bioanalysis, 3(13), 1457-1470.

DOI: 10.4155/bio.11.117

[7] Zinchenko, K., Wu, C. Y., and Song, K. T. (2016). "A study on speech recognition control for a surgical robot." IEEE Transactions on Industrial Informatics, 13(2), 607-615.

DOI: 10.1109/tii.2016.2625818

[8] Elazzazi, M., Jawad, L., Hilfi, M., and Pandya, A. (2022). "A Natural Language Interface for an Autonomous Camera Control System on the da Vinci Surgical Robot." Robotics 2022, 11, 40.

DOI: 10.3390/robotics11020040

[9] Pocketsphinx repository from CMU Sphinx.https://github.com/cmusphinx/pocketsphinx. Last Access: 2023-01-16.

[10] Manasa, C. S., Priya, K. J., and Gupta, D. (2019). "Comparison of acoustical models of GMMHMM based for speech recognition in Hindi using PocketSphinx." 3rd International Conference on Computing Methodologies and Communication (ICCMC), pp.534-539. IEEE.

DOI: 10.1109/iccmc.2019.8819747

[11] Povey, D., et al. (2011). "The Kaldi speech recognition toolkit." IEEE 2011 workshop on automatic speech recognition and understanding (No. CONF). IEEE Signal Processing Society.

DOI: 10.1109/asru.2011.6163923

[12] Hannun, Awni, et al. (2014). "Deep speech: Scaling up end-to-end speech recognition." arXiv preprint arXiv:1412.5567.

[13] Mozilla Common Voice Dataset. https://commonvoice.mozilla.org/en. Last Access: 2023-01- 16.

[14] Vosk Website. https://alphacephei.com/vosk/. Last Access: 2023-01-16.[15] Radford, A., et al. (2022). "Robust speech recognition via large-scale weak supervision." arXiv preprint arXiv:2212.04356.

[16] Errattahi, R., Hannani, A.E., and Ouahmane, H. (2015). "Automatic Speech Recognition Errors Detection and Correction: A Review." International Conference on Natural Language and Speech Processing.

DOI: 10.1016/j.procs.2018.03.005

[17] McCowan, I.A., Moore, D., Dines, J., Gatica-Perez, D., Flynn, M., Wellner, P., Bourlard, H. (2004). "On the use of information retrieval measures for speech recognition evaluation." Technical Report. IDIAP.

[18] Mostefa, D., Hamon, O., and Choukri, K. (2006). "Evaluation of Automatic Speech Recognition and Speech Language Translation within TC-STAR: Results from the first evaluation campaign." LREC, pp.149-154.

[19] JiWER: Similarity measures for automatic speech recognition evaluation. https://github.com/jitsi/jiwer. Last access: 2023-01-16.