@inproceedings{malisz2019modern,
  title={Modern speech synthesis for phonetic sciences: a discussion and an evaluation},
  author={Malisz, Zofia and Henter, Gustav Eje and Valentini-Botinhao, Cassia and Watts, Oliver and Beskow, Jonas and Gustafson, Joakim},
  booktitle={Proc. ICPhS},
  abstract={Decades of gradual advances in speech synthesis have recently culminated in exponential improvements fuelled by deep learning. This quantum leap has the potential to finally deliver realistic, controllable, and robust synthetic stimuli for speech experiments. In this article, we discuss these and other implications for phonetic sciences. We substantiate our argument by evaluating classic rule-based formant synthesis against state-of-the-art synthesisers on a) subjective naturalness ratings and b) a behavioural measure (reaction times in a lexical decision task). We also differentiate between text-to-speech and speech-to-speech methods. Naturalness ratings indicate that all modern systems are substantially closer to natural speech than formant synthesis. Reaction times for several modern systems do not differ substantially from natural speech, meaning that the processing gap observed in older systems, and reproduced with our formant synthesiser, is no longer evident. Importantly, some speech-to-speech methods are nearly indistinguishable from natural speech on both measures.},
  keywords={speech synthesis, scientific methodology, speech technology},
  address={Melbourne, Australia},
  month={Aug.},
  publisher={IPA},
  volume={19},
  pages={487--491},
  url={http://intro2psycholing.net/ICPhS/papers/ICPhS\_536.pdf},
  year={2019}
}