References

1. [1]A. v. d. Oord, S. Dieleman, H. Zen et al., “Wavenet: A generative model for raw audio,” arXiv preprint arXiv:1609.03499, 2016. [2] J. Shen, R. Pang, R. J. Weiss et al., “Natural tts synthesis by conditioning wavenet on mel spectrogram predictions,” ICASSP, 2018. [3] Y. Jia, Y. Zhang, R. J. Weiss et al., “Transfer learning from speaker verification to multispeaker text-to-speech synthesis,” in Advances in neural information processing systems, 2018. [4] R. Kumar and M. Singh, “Ai-powered voice cloning for assistive tech- nologies: A user-centric perspective,” Journal of Assistive Technologies, vol. 16, no. 3, pp. 123–132, 2022. [5] M.-H. Maras and A. Alexandrou, “Determining authenticity of audio deepfakes: Legal and ethical implications,” Forensic Science Interna- tional: Reports, vol. 2, p. 100090, 2020. [6] H. Zen, K. Tokuda, and A. W. Black, “Statistical parametric speech synthesis,” Speech Communication, vol. 51, no. 11, pp. 1039–1064, 2009. [7] K. Qian, Y. Zhang, S. Chang, X. Yang, and M. Hasegawa-Johnson, “Autovc: Zero-shot voice style transfer with only autoencoder loss,” arXiv preprint arXiv:1905.05879, 2019. [8] M. Binkowski, C. Donahue, and S. Dieleman, “High fidelity speech synthesis with adversarial networks,” arXiv preprint arXiv:1909.11646, 2019. [9] K. Kumar, R. Kumar, J. de Boissiere et al., “Melgan: Generative adversarial networks for conditional waveform synthesis,” Advances in Neural Information Processing Systems, vol. 32, 2019. [10] Y. Ren, C. Hu, X. Tan, J. He, S. Zhao, Z. Zhao, and T. Qin, “Fastspeech 2: Fast and high-quality end-to-end text to speech,” in International Conference on Learning Representations (ICLR), 2021. [11] J. Kim, S. Kim, B. Jung, B.-J. Kim, and S. Yoon, “Conditional variational autoencoder with adversarial learning for end-to-end text- to-speech,” in Proceedings of the 38th International Conference on Machine Learning, 2021. [12] L. Wan, Q. Wang, A. Papir, and I. L. Moreno, “Generalized end-to-end loss for speaker verification,” arXiv preprint arXiv:1710.10467, 2018. [13] J. Kong, J. Kim, and J. Bae, “Hifi-gan: Generative adversarial net- works for efficient and high fidelity speech synthesis,” arXiv preprint arXiv:2010.05646, 2020. [14] M. Wester and J. Latorre, “Synthesis of personalized speech using deep neural networks,” in Interspeech, 2016. [15] E. Cooper and A. Singh, “Synthetic speech in audiobook production: Enhancing accessibility and performance,” Journal of Audio Engineer- ing, vol. 68, no. 3, 2020. [16] D. Jiang, H. Zhang, W.-N. Wang, and X. Liu, “Deep voice cloning for language dubbing,” Multimedia Tools and Applications, vol. 79, no. 39, pp. 29 537–29 557, 2020. [17] J. Yamagishi and S. King, “Speech synthesis technologies for individuals with vocal disabilities,” in Interspeech, 2012. [18] S. Kreps, P. McCain, and M. Brundage, “Deepfake technology and the risk of audio fraud,” Brookings TechStream, 2021. [19] J. Vincent, “The art and ethics of deepfake music,” The Verge, 2020, available at: https://www.theverge.com/2020/9/24/21453827. [20] R. Skerry-Ryan, E. Battenberg, Y. Xiao, Y. Wang, D. Stanton, J. Shor et al., “Towards end-to-end prosody transfer for expressive speech syn- thesis with tacotron,” in International Conference on Machine Learning, 2018. [21] C. Zhang, Y. Liu, and S. Narayanan, “Towards robust and generalizable voice cloning in unseen conditions,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 1253–1266, 2022. [22] T. Kinnunen, H. Delgado, M. Todisco, M. Sahidullah, N. Evans, J. Yamagishi, and K. A. Lee, “Asvspoof 2019: Automatic speaker verification spoofing and countermeasures challenge evaluation plan,” in INTERSPEECH, 2020. [23] T. M¨uller and D. Kolossa, “Signature detection of synthesized speech from phase and lpc residual cues,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 2159–2171, 2021. [24] E. Albadawy, A. Lopatka, and K. Patil, “Detecting audio deepfakes using parallel wavegan,” in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020, pp. 2587–2591. [25] P. Mittal, P. Verma, and S. Saxena, “Contrastive representation learning for deepfake audio detection,” arXiv preprint arXiv:2301.11289, 2023. [26] Y. Koizumi, K. Sonobe, Y. Kawaguchi, and T. Toda, “Detection of adver- sarial examples for voice spoofing countermeasures using inconsistency in speech features,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 291–304, 2022.