@inproceedings{zarriess-etal-2017-refer,
    title = "Refer-i{TTS}: A System for Referring in Spoken Installments to Objects in Real-World Images",
    author = "Zarrie{\ss}, Sina  and
      L{\'o}pez Gambino, M. Soledad  and
      Schlangen, David",
    editor = "Alonso, Jose M.  and
      Bugar{\'i}n, Alberto  and
      Reiter, Ehud",
    booktitle = "Proceedings of the 10th International Conference on Natural Language Generation",
    month = sep,
    year = "2017",
    address = "Santiago de Compostela, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/W17-3509/",
    doi = "10.18653/v1/W17-3509",
    pages = "72--73",
    abstract = "Current referring expression generation systems mostly deliver their output as one-shot, written expressions. We present on-going work on incremental generation of spoken expressions referring to objects in real-world images. This approach extends upon previous work using the words-as-classifier model for generation. We implement this generator in an incremental dialogue processing framework such that we can exploit an existing interface to incremental text-to-speech synthesis. Our system generates and synthesizes referring expressions while continuously observing non-verbal user reactions."
}