@article{sarfjoo2019transformation,
  title={Transformation of low-quality device-recorded speech to high-quality speech using improved {SEGAN} model},
  author={Sarfjoo, Seyyed Saeed and Wang, Xin and Henter, Gustav Eje and Lorenzo-Trueba, Jaime and Takaki, Shinji and Yamagishi, Junichi},
  journal={arXiv preprint arXiv:1911.03952},
  abstract={Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this research was to study the automatic generation of high-quality speech from such low-quality device-recorded speech, which could then be applied to many speech-generation tasks. In this paper, we first introduce our new device-recorded speech dataset then propose an improved end-to-end method for automatically transforming the low-quality device-recorded speech into professional high-quality speech. Our method is an extension of a generative adversarial network (GAN)-based speech enhancement model called speech enhancement GAN (SEGAN), and we present two modifications to make model training more robust and stable. Finally, from a large-scale listening test, we show that our method can significantly enhance the quality of device-recorded speech signals.},
  keywords={audio transformation, speech enhancement, generative adversarial network, speech synthesis},
  month={Nov.},
  year={2019}
}