International Journal of Applied Science and Engineering

Published by Chaoyang University of Technology

Aakash Ezhilan, R. Dheekksha, S. Shridevi*

Centre for Advanced Data Science, Vellore Institute of Technology, Chennai, India


 

Download Citation: |
Download PDF


ABSTRACT


Style transfer is one of the most popular uses of neural networks. It has been thoroughly researched, such as extracting the style from famous paintings and applying it to other images thus creating synthetic paintings. Generative adversarial networks (GANs) are used to achieve this. This paper explores the many ways in which the same results can be achieved with audio related tasks, for which a plethora of new applications can be found. Analysis of different techniques used to transfer styles of audios, specifically changing the gender of the audio is implemented. The Crowd sourced high-quality UK and Ireland English Dialect speech data set was used. In this paper, the input is the male or female wave form and the opposite gender’s waveform is synthesized by the network, with the content spoken remaining the same. Different architectures are explored, from naive techniques and directly training audio waveforms against convolution neural networks (CNN) to using extensive algorithms researched for image style conversion and generation of spectrograms (using GANs) to be trained on CNNs. This research has a broader scope when used in converting music from one genre to another, identification of synthetic voices, curating voices for AIs based on preference etc.


Keywords: Style transfer, Audio analysis, Neural networks, Dialect transfer.


Share this article with your colleagues

 


REFERENCES


  1. Chen, J., Yang, G., Zhao, H., Ramasamy, M. 2020. Audio style transfer using shallow convolutional networks and random filters, Multimedia Tools and Applications. Doi :10.1007/s11042-020-08798-6.

  2. Demirsahin, I., Kjartansson, O., Gutkin, A., Rivera, C. 2020. Open-source Multi-speaker corpora of the English accents in the British Isles, Vol. Proceedings of the 12th Language Resources and Evaluation Conference, European Language Resources Association, Marseille, France, 6532–6541. URL https://www.aclweb.org/ anthology/2020.lrec1.804

  3. Deshpande, M.S., Chadha, V.S., Lin, V. 2019. Audio style transfer for accents. URL https://shuby.de/files/11-785_project.pdf

  4. Grinstein, E., Duong, N.Q.K., Ozerov, A. 2018. P. Perez, Audio style transfer, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). doi:10.1109/icassp.2018.8461711.

  5. Hayashi, T., Tamamori, A., Kobayashi, K., Takeda, K., Toda, T. 2017. An investigation of multi-speaker training for wavenet vocoder, in 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). 712–718. http://dx.doi.org/10.1109/ICASSP.2018.8461711

  6. Hsu, C.-C., Hwang, H.-T., Wu, Y.-C., Tsao, Y., Wang, H.M. 2017. Voice conversion from unaligned corpora using variational auto encoding Wasserstein generative adversarial networks, arXiv:1704.00849.

  7. Huang, C.-y., Lin, Y.Y., Lee, H.-y., Lee, L.-s. 2020. Defending your voice: Adversarial attack on voice conversion, ArXiv, vol. abs/2005.08781.

  8. Kameoka, H., Kaneko, T., Tanaka, K., Hojo, N. 2018. StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks, arXiv: 1806.02169 [cs.SD].

  9. Lorenzo-Trueba, J., Yamagishi, J., Toda, T., Saito, D., Villavicencio, F., Kinnunen, T., Ling, Z. 2018. The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods, preprint arXiv:1804.04262.

  10. Miyoshi, H., Saito, Y., Takamichi, S., Saruwatari, H. 2017. Voice conversion using sequence-to-sequence learning of context posterior probabilities, preprint arXiv: 1704.02360.

  11. Pasini, M. 2019. MelGAN-VC: Voice conversion and audio style transfer on arbitrarily long samples using Spectrograms. https://arxiv.org/abs/1910.03713

  12. Sisman, B., Yamagishi, J., King, S., Li, H. 2020. An overview of voice conversion and its challenges: from statistical modeling to deep learning. arXiv preprint, arXiv:2008.03648v2

  13. Tamamori, A., Hayashi, T., Kobayashi, K., Takeda, K., Toda, T. 2017. Speaker-dependent wave net vocoder., in Proc. Interspeech, 1118–1122.

  14. Verma, P, Smith, J.O. 2018. Neural style Transfer for audio spectograms, CoRR abs/1801.01589. URL http://arxiv.org/abs/1801.01589

  15. Wester, M., Wu, Z., Yamagishi, J. 2016. Analysis of the voice conversion challenge 2016 evaluation results., in Proc. Interspeech, 1637–1641.

  16. Wu, C.-W., Liu, J.-Y., Yang, Y.-H., Jang, J.-S.R. 2018. Singing style transfer using Cycle-consistent boundary equilibrium generative adversarial network. arXiv:1807.02254


ARTICLE INFORMATION


Received: 2021-01-29

Accepted: 2021-04-07
Publication Date: 2021-09-01


Cite this article:

Ezhilan, A., Dheekksha, R., Shridevi, S. 2021. Audio style conversion using deep learning, International Journal of Applied Science and Engineering. 18, 2021034. https://doi.org/10.6703/IJASE.202109_18(5).004

  Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.


We use cookies on this website to improve your user experience. By using this site you agree to its use of cookies.