Abstract
This paper assesses the interest of the multiscale Wavelet Scattering Transform (WST) for Speaker identification (SI) applied in several depths and invariance scales. Our primary purpose is to present an approach to optimally design the WST to enhance the identification accuracy for short utterances. We describe the invariant features offered by the depth of this transform by performing simple experiments based on text-independent and text-dependent SI. To compete the state-of-the-art (SOTA), we propose a fusion method between WST and x-vectors architecture, we show that this structure outperforms HWSTCNN by \(7.57\%\) on TIMIT dataset sampled at 8 kHz and makes the same performance in the SOTA at 16 kHz.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andén, J., Mallat, S.: Deep scattering spectrum. IEEE Trans. Signal Process. 62(16), 4114–4128 (2014). https://doi.org/10.1109/TSP.2014.2326991
Garofolo, J.S.: Timit acoustic phonetic continuous speech corpus. Linguistic Data Consortium, 1993 (1993)
Ghezaiel, W., Brun, L., Lézoray, O.: Hybrid network for end-to-end text-independent speaker identification. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2352–2359 (2021). https://doi.org/10.1109/ICPR48806.2021.9413293
Lagrange, M., Andrieu, H., Emmanuel, I., Busquets, G., Loubrié, S.: Classification of rainfall radar images using the scattering transform. J. Hydrol. 556, 972–979 (2018)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Li, B.H., Zhang, J., Zheng, W.S.: Hep-2 cells staining patterns classification via wavelet scattering network and random forest. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 406–410. IEEE (2015)
Mallat, S.: A wavelet tour of signal processing. Elsevier (1999)
Mallat, S.: Group invariant scattering. Commun. Pure Appl. Math. 65(10), 1331–1398 (2012)
Mallat, S.: Understanding deep convolutional networks. Philos. Trans. R. Soc. A: Math. Phys. Eng. Sci. 374(2065), 20150203 (2016)
Minaee, S., Abdolrashidi, A., Wang, Y.: Iris recognition using scattering transform and textural features. In: 2015 IEEE signal processing and signal processing education workshop (SP/SPE), pp. 37–42. IEEE (2015)
Muckenhirn, H., Magimai-Doss, M., Marcel, S.: On learning vocal tract system related speaker discriminative information from raw signal using CNNs. In: INTERSPEECH, pp. 1116–1120 (2018)
Rasti, P., Ahmad, A., Samiei, S., Belin, E., Rousseau, D.: Supervised image classification by scattering transform with application to weed detection in culture crops of high density. Remote Sens. 11(3), 249 (2019). https://doi.org/10.3390/rs11030249. https://www.mdpi.com/2072-4292/11/3/249
Ravanelli, M., Bengio, Y.: Speaker recognition from raw waveform with sincNet. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 1021–1028 (2018). https://doi.org/10.1109/SLT.2018.8639585
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 (2018). https://doi.org/10.1109/ICASSP.2018.8461375
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
Moufidi, A., Rousseau, D., Rasti, P. (2023). Wavelet Scattering Transform Depth Benefit, An Application for Speaker Identification. In: El Gayar, N., Trentin, E., Ravanelli, M., Abbas, H. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2022. Lecture Notes in Computer Science(), vol 13739. Springer, Cham. https://doi.org/10.1007/978-3-031-20650-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-20650-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20649-8
Online ISBN: 978-3-031-20650-4
eBook Packages: Computer ScienceComputer Science (R0)