Abstract
An approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal recorded employing 7 speakers who spoke English at the native or near-native speaker level withing a Standard Southern British English variety accent. The recordings were analyzed by specialists from the field of phonology in order to extract vocalic segments and selected allophones. Then parameterization was made using Mel Frequency Cepstral Coefficients, Delta MFCC, and Delta Delta MFCC. In the next stage, feature vectors were passed to the input of individual algorithms utilized to reduce the size of the vector by previously mentioned algorithms. The vectors prepared in this way have been used for classifying allophones and vocalic segments employing simple Artificial Neural Network (ANN) and Support Vector Machine (SVM). The classification results using both classifiers and methods applied for reducing the number of parameters were presented. The results of the reduction are also shown explicitly, by indicating parameters proven to be significant and those rejected by particular algorithms. Factors influencing the obtained results were discussed. Difficulties associated with obtaining the data set, its labeling, and research on allophones were also analyzed.
Dataset employed in this research available at website: https://modality-corpus.org in ALOFON corpus section.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Karpagavalli, S., Chandra, E.: A review on automatic speech recognition architecture and approaches. Int. J. Sig. Process. Image Process. Pattern Recogn. 9(4), 393–404 (2016)
Xu, D., Qian, H., Xu, Y.: The state of the art in human–robot interaction for household services (chap. 6.1). In: Xu, D., Qian, H., Xu, Y. (eds.) Household Service Robotics, pp. 457–465. Academic Press, Oxford (2015)
Piotrowska, M., Korvel, G., Kurowski, A., Kostek, B., Czyzewski, A.: Machine learning applied to aspirated and non-aspirated allophone classification—An approach based on audio ‘Fingerprinting’. In: 145 Audio Engineering Society Convention (2018)
Recasens, D.: A cross-language acoustic study of initial and final allophones of /l/. Speech Commun. 54(3), 368–383 (2012)
German, J.S., Carlson, K., Pierrehumbert, J.B.: Reassignment of consonant allophones in rapid dialect acquisition. J. Phon. 41(3–4), 228–248 (2013)
Drahanský, M., Orság, F.: Fingerprints and speech recognition as parts of the biometry. In: Proceedings of 36th International Conference MOSIS, pp. 177–183 (2002)
Noordenbos, M.W., Segers, E., Serniclaes, W., Mitterer, H., Verhoeven, L.: Allophonic mode of speech perception in Dutch children at risk for dyslexia: a longitudinal study. Res. Dev. Disabil. 33(5), 1469–1483 (2012)
Zaporowski, S., Cygert, S., Szwoch, G., Korvel, G., Czyżewski, A.: Rejestracja, parametryzacja i klasyfikacja alofonów z wykorzystaniem bimodalności (2018)
Piotrowska, M., Korvel, G., Kostek, B., Ciszewski, T., Czyzewski, A.: Machine learning-based analysis of English lateral allophones. Int. J. Appl. Math. Comput. Sci. 29(2), 393–405 (2019)
Zaporowski, S., Czyżewski, A.: Selection of features for multimodal vocalic segments classification. In: Choroś, K., Kopel, M., Kukla, E., Siemiński, A. (eds.) MISSI 2018. AISC, vol. 833, pp. 490–500. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-98678-4_49
Jeevan, M., Dhingra, A., Hanmandlu, M., Panigrahi, B.K.: Robust speaker verification using GFCC based i-vectors. In: Lobiyal, D., Mohapatra, D.P., Nagar, A., Sahoo, M. (eds.) Proceedings of the International Conference on Signal, Networks, Computing, and Systems. LNEE, vol. 395, pp. 85–91. Springer, New Delhi (2017). https://doi.org/10.1007/978-81-322-3592-7_9
Xu, J., Si, Y., Pan, J., Yan, Y.: Automatic allophone deriving for Korean speech recognition. In: Proceedings - 9th International Conference on Computational Intelligence and Security, CIS 2013, pp. 776–779 (2013)
Korvel, G., Kostek, B.: Examining feature vector for phoneme recognition. In: 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pp. 394–398 (2017)
Kostek, B., Piotrowska, M., Ciszewski, T., Czyzewski, A.: No comparative study of self-organizing maps vs subjective evaluation of quality of allophone pronunciation for non-native English speakers. In: Audio Engineering Society Convention 143 (2017)
Kostek, B., et al.: Report of the ISMIS 2011 contest: music information retrieval. In: Kryszkiewicz, M., Rybinski, H., Skowron, A., Raś, Z.W. (eds.) ISMIS 2011. LNCS (LNAI), vol. 6804, pp. 715–724. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21916-0_75
Sikora, T., Kim, H.G., Moreau N.: MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval. Wiley, Hoboken (2005)
Eringis, D., Tamulevičius, G.: Modified filterbank analysis features for speech recognition. Baltic J. Mod. Comput. 3(1), 29–42 (2015)
Zheng, F., Zhang, G., Song, Z.: Comparison of different implementations of MFCC. J. Comput. Sci. Technol. 16, 582–589 (2001). https://doi.org/10.1007/BF02943243
Multimedia Systems Department: Modality Corpus (2018). http://modality-corpus.org/. Accessed 13 Feb 2020
Cygert, S., Szwoch, G., Zaporowski, S., Czyzewski, A.: Vocalic segments classification assisted by mouth motion capture. In: 2018 11th International Conference on Human System Interaction (HSI), pp. 318–324 (2018)
Bro, R., Smilde, A.K.: Principal component analysis. Anal. Methods 6, 2812–2831 (2014)
Abdi, H., Williams, L.J.: Principal component analysis. Wiley Interdiscip. Rev. Comput. Stat. 2(4), 433–459 (2010)
Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006). https://doi.org/10.1007/s10994-006-6226-1
Louppe, G., Wehenkel, L., Sutera, A., Geurts, P.: Understanding variable importances in forests of randomized trees. Adv. Neural. Inf. Process. Syst. 26, 431–439 (2013)
Svetnik, V., Liaw, A., Tong, C., Culberson, J.C., Sheridan, R.P., Feuston, B.P.: Random forest: a classification and regression tool for compound classification and QSAR modeling. J. Chem. Inf. Comput. Sci. 43(6), 1947–1958 (2003)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2012)
Mao, Y., Pi, D., Liu, Y., Sun, Y.: Accelerated recursive feature elimination based on support vector machine for key variable identification. Chin. J. Chem. Eng. 14, 65–72 (2006)
Chollet, F.: Keras (2015). https://keras.io. Accessed 10 Sept 2018
Acknowledgment
Research sponsored by the Polish National Science Centre, Dec. No. 2015/17/B/ST6/01874.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zaporowski, S., Czyżewski, A. (2020). Audio Feature Analysis for Precise Vocalic Segments Classification in English. In: Dziech, A., Mees, W., Czyżewski, A. (eds) Multimedia Communications, Services and Security. MCSS 2020. Communications in Computer and Information Science, vol 1284. Springer, Cham. https://doi.org/10.1007/978-3-030-59000-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-59000-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58999-8
Online ISBN: 978-3-030-59000-0
eBook Packages: Computer ScienceComputer Science (R0)