Abstract
In forensic speaker recognition, the speaker’s vocal tract length (VTL) is an important factor. In this work formant frequency analysis of Malayalam vowels were carried out on sound samples collected from 100 speakers and their vocal tract lengths were found experimentally. We have estimated vocal tract length for five Malayalam vowel sounds for different speakers. Using formant frequencies, the effect of VTL on vowel production variation have been investigated here. Data were collected from 100 participants (52 females and 48 males) in five Malayalam vowels /a/, /e/, /u/, /ae/, and /o/. Each vowel was recorded ten times. The accuracy of the formant extraction technique is highly sensitive to the quality of the input sample. It works best with samples that don’t have any noise, but its performance goes down when it’s used with noisy data. The vocal tract was estimated using Pink Noise, White Gaussian Noise, and Red Noise with signal-to-noise ratios (SNRs) ranging from −20 dB to +20 dB. The autocorrelation-based formant extraction is a good way to find vocal tracts when there is a lot of noise in the background. This strategy improves the accuracy of VTL extraction even at extremely high noise levels (−20 dB) compared to previous research. This information is extremely valuable for forensic speaker recognition difficulties in environments with heavy background noise. The VTL can be employed for speaker normalization and parameter extraction.
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
References
Fant, G.: Acoustic Theory of Speech Production. Mouton, The Hague, The Netherlands (1960)
Kelly, J., Lochbaum, C.: Speech synthesis. In: Proceedings of the International Conference on Acoustics (1962)
Perkell, J.S.: Physiology of Speech Production: Results and Implications of Quantitative Cineradiography Study. MIT, Cambridge, MA (1969)
Cantoni, V., Dimov, D., Tistarelli, M. (eds.): Biometric Authentication: First International Workshop, BIOMET 2014, Sofia, Bulgaria, 23–24 June 2014. Revised Selected Papers, vol. 8897. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13386-7
Kumar, M.: Forensic speaker identification: a review of literature and reflection on future. Lang. India 19(7), 163–176 (2019)
Neustein, A., Patil, H.A.: Forensic Speaker Recognition, vol. 1. Springer, New York (2012). https://doi.org/10.1007/978-1-4614-0263-3
Lammert, A.C., Narayanan, S.S.: On short-time estimation of vocal tract length from formant frequencies. PLoS ONE 10(7), e0132193 (2015)
Tuller, B., Fitch, H.L.: Preservation of vocal tract length in speech: a negative finding. J. Acoust. Soc. Am. 67(3), 1068–1071 (1980)
Wood, S.: The acoustical significance of tongue, lip, and larynx maneuvers in rounded palatal vowels. J. Acoust. Soc. Am. 80(2), 391–401 (1986)
Sundberg, J., Nordström, P.-E.: Raised and lowered larynx – the effect on vowel formant frequencies. STLQPRS2-3/1976, pp. 33–39 (1976)
Hoole, P., Kroos, C.: Control of larynx height in vowel production. In: 5th International Conference on Spoken Language Processing, Sydney, Australia (1998)
Ananthapadmanabha, T.V., Ramakrishnan, A.G., Sharma, S.: Significance of the levels of spectral valleys with application to front/back distinction of vowel sounds. https://arxiv.org/abs/1506.04828 (2015)
Wakita, H.: Normalization of vowels by vocal-tract length and its application to vowel identification. IEEE Trans. Acoust. Speech Signal Process. 25, 183–192 (1977)
Yegnanarayana, B., Veldhuis, R.N.J.: Extraction of vocal-tract system characteristics from speech signals. IEEE Trans. Speech Audio Process. 6(4), 313–327 (1998)
Tsutsumi, K., Kagawa, Y.: Extraction of transfer characteristics of vocal tract from speech signals. In: Inverse Problems in Engineering Mechanics II, pp. 477–484. Elsevier Science Ltd. (2000)
Kesarkar, M.P., Rao, P.: Feature extraction for speech recognition. Electronic Systems, EE. Department, IIT Bombay (2003)
Fitch, W.T.: Vocal tract length and formant frequency dispersion correlate with body size in rhesus macaques. J. Acoust. Soc. Am. 102(2), 1213–1222 (1997)
Pisanski, K., et al.: Volitional exaggeration of body size through fundamental and formant frequency modulation in humans. Sci. Rep. 6(1), 34389 (2016)
Lass, N.J., Brown, W.S.: Correlational study of speakers’ heights, weights, body surface areas, and speaking fundamental frequencies. J. Acoust. Soc. Am. 63(4), 1218–1220 (1978)
Bharathi, B., Kavitha, S., MohanaPriya, K.: Speaker verification in a noisy environment by enhancing the speech signal using various approaches of spectral subtraction. In: 2016 10th International Conference on Intelligent Systems and Control (ISCO). IEEE (2016)
Dev, A., Bansal, P.: Robust features for noisy speech recognition using MFCC computation from magnitude spectrum of higher order autocorrelation coefficients. Int. J. Comput. Appl. 10(8), 36–38 (2010)
Bansal, P., Dev, A., Jain, S.B.: Novel feature vector set extraction using spectral peaks in autocorrelation domain. J. Inf. Comput. Sci. 4(2), 131–141 (2009)
Bibish Kumar, K.T., Sunil Kumar, R.K.: Viseme identification and analysis for recognition of Malayalam speech intense background noise. Ph.D. thesis (2021)
Shannon, B.J., Paliwal, K.K.: Feature extraction from higher-lag autocorrelation coefficients for robust speech recognition. Speech Commun. 48(11), 1458–1485 (2006)
Farahani, G.: Autocorrelation-based noise subtraction method with smoothing, overestimation, energy, and cepstral mean and variance normalization for noisy speech recognition. EURASIP J. Audio Speech Music Process. 2017(1), 1–16 (2017)
Vorperian, H., Kent, R., Lindstrom, M.J., Kalina, C.M., Gentry, L.R., et al.: Development of vocal tract length during early childhood: a magnetic resonance imaging study. J. Acoust. Soc. Am. 117, 338–350 (2005)
Fitch, W., Giedd, J.: Morphology and development of the human vocal tract: a study using magnetic resonance imaging. J. Acoust. Soc. Am. 106, 1511–1522 (1999)
Vorperian, H., Wang, S., Chung, M., Schimek, E., Durtschi, R., et al.: Anatomic development of the oral and pharyngeal portions of the vocal tract: an imaging study. J. Acoust. Soc. Am. 125, 1666–1678 (2009)
Farahani, G., Ahadi, S.M.: Robust features for noisy speech recognition based on filtering and spectral peaks in autocorrelation domain. In: 2005 13th European Signal Processing Conference. IEEE (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 IFIP International Federation for Information Processing
About this paper
Cite this paper
Aljinu Khadar, K.V., Sunil Kumar, R.K., Sameer, V.V. (2023). Extraction of Vocal Tract Length from Formant Frequencies for Forensic Speech Applications in Noisy Environment. In: Chandran K R, S., N, S., A, B., Hamead H, S. (eds) Computational Intelligence in Data Science. ICCIDS 2023. IFIP Advances in Information and Communication Technology, vol 673. Springer, Cham. https://doi.org/10.1007/978-3-031-38296-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-38296-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38295-6
Online ISBN: 978-3-031-38296-3
eBook Packages: Computer ScienceComputer Science (R0)
