Abstract
Developing an automatic speaker verification (ASV) system for children is extremely challenging due to the rarity of children’s speech corpora. To deal with data scarcity, we have developed an out-of-domain data augmentation technique in this work. For that purpose, we have resorted to pitch scaling, formant modification, time-scale modification, and voice-conversion of adults’ speech in order to render it acoustically similar to children’s speech. The children’s speech along with the modified and original adults’ data are then pooled into training. Furthermore, two complementary front-end features namely, Mel-frequency cepstral coefficients (MFCC) and frequency-domain linear prediction (FDLP) coefficients have been concatenated so as to simultaneously capture the spectral as well as temporal envelopes. The feature concatenation approach when combined with data augmentation helps in achieving an overall relative reduction of \(50.2\%\) in equal error rate.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Athineos, M., Ellis, D.: Frequency-domain linear prediction for temporal features. In: 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721), pp. 261–266 (2003)
Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357–366 (1980). https://doi.org/10.1109/TASSP.1980.1163420
Eskenazi, M., Mostow, J., Graff, D.: The CMU Kids Corpus LDC97S63. https://catalog.ldc.upenn.edu/LDC97S63 (1997)
Kaneko, T., Kameoka, H.: Parallel-data-free voice conversion using cycle-consistent adversarial networks. arXiv preprint arXiv:1711.11293 (2017)
Kumar, V., Kumar, A., Shahnawazuddin, S.: Creating robust children’s ASR system in zero-resource condition through out-of-domain data augmentation. Circuits Syst. Signal Process. 41(4), 2205–2220 (2022)
Lee, S., Potamianos, A., Narayanan, S.S.: Acoustics of children’s speech: developmental changes of temporal and spectral parameters. J. Acoust. Soc. Am. 105(3), 1455–1468 (1999). https://doi.org/10.1121/1.426686
Mantena, G., Achanta, S., Prahallad, K.: Query-by-example spoken term detection using frequency domain linear prediction and non-segmental dynamic time warping. IEEE/ACM Trans. Audio Speech Lang. Process. 22(5), 946–955 (2014)
Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Proceedings of the INTERSPEECH (2015)
Povey, D., et al.: The Kaldi Speech recognition toolkit. In: Proceedings of the ASRU (2011)
Povey, D., et al.: The kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. No. CONF, IEEE Signal Processing Society (2011)
Povey, D., Zhang, X., Khudanpur, S.: Parallel training of DNNs with natural gradient and parameter averaging. arXiv preprint arXiv:1410.7455 (2014)
Prasanna, S.R.M., Govind, D., Rao, K.S., Yegnanarayana, B.: Fast prosody modification using instants of significant excitation. In: Proceedings of the International Conference on Speech Prosody (2010)
Quateier, T.F.: Discrete Time Processing of Speech Signals- Principles and Practice (1997)
Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: WSJCAMO: a British english speech corpus for large vocabulary continuous speech recognition. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 81–84. IEEE (1995)
Russell, M., D’Arcy, S.: Challenges for computer recognition of children’s speech. In: Proceedings of the Speech and Language Technologies in Education (SLaTE) (2007)
Russell, M., D’Arcy, S., Wong, M., Batliner, A., Blomberg, M., Gerosa, M.: The pf-star children’s speech corpus. In: Interspeech 2005 (2005)
Safavi, S., Najafian, M., Hanani, A., Russell, M.J., Jancovic, P.: Comparison of speaker verification performance for adult and child speech. In: Proceedings of the WOCCI (2014)
Safavi, S., Najafian, M., Hanani, A., Russell, M.J., Jancovic, P., Carey, M.J.: Speaker recognition for children’s speech. arXiv arXiv:1609.07498 (2012)
Safavi, S., Russell, M., Jancovic, P.: Automatic speaker, age-group and gender identification from children’s speech. Comput. Speech Lang. 50, 141–156 (2018)
Shahnawazuddin, S., Adiga, N., Kathania, H.K., Sai, B.T.: Creating speaker independent ASR system through prosody modification based data augmentation. Pattern Recogn. Lett. 131, 213–218 (2020). https://doi.org/10.1016/j.patrec.2019.12.019
Shahnawazuddin, S., Ahmad, W., Adiga, N., Kumar, A.: In-domain and out-of-domain data augmentation to improve children’s speaker verification system in limited data scenario. In: Proceedings of the ICASSP, pp. 7554–7558 (2020). https://doi.org/10.1109/ICASSP40776.2020.9053891
Shahnawazuddin, S., Ahmad, W., Adiga, N., Kumar, A.: Children’s speaker verification in low and zero resource conditions. Digit. Signal Process. 116, 103115 (2021)
Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Proceedings of the INTERSPEECH, pp. 999–1003 (August 2017)
Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: Robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329–5333. IEEE (2018)
Stevens, S.S., Volkmann, J., Newman, E.B.: A scale for the measurement of the psychological magnitude pitch. J. Acoust. Soc. Am. 8(3), 185–190 (1937)
Thomas, S., Ganapathy, S., Hermansky, H.: Recognition of reverberant speech using frequency domain linear prediction. IEEE Signal Process. Lett. 15, 681–684 (2008)
Wickramasinghe, B., Irtza, S., Ambikairajah, E., Epps, J.: Frequency domain linear prediction features for replay spoofing attack detection. In: Interspeech, pp. 661–665 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Aziz, S., Pushp, S., Shahnawazuddin, S. (2023). Studying the Effectiveness of Data Augmentation and Frequency-Domain Linear Prediction Coefficients in Children’s Speaker Verification Under Low-Resource Conditions. In: Karpov, A., Samudravijaya, K., Deepak, K.T., Hegde, R.M., Agrawal, S.S., Prasanna, S.R.M. (eds) Speech and Computer. SPECOM 2023. Lecture Notes in Computer Science(), vol 14339. Springer, Cham. https://doi.org/10.1007/978-3-031-48312-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-48312-7_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48311-0
Online ISBN: 978-3-031-48312-7
eBook Packages: Computer ScienceComputer Science (R0)