Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images

Sina Zarrieß, M. Soledad López Gambino, David Schlangen


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.
Anthology ID:
W17-3509
Volume:
Proceedings of the 10th International Conference on Natural Language Generation
Month:
September
Year:
2017
Address:
Santiago de Compostela, Spain
Editors:
Jose M. Alonso, Alberto Bugarín, Ehud Reiter
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
72–73
Language:
URL:
https://aclanthology.org/W17-3509
DOI:
10.18653/v1/W17-3509
Bibkey:
Cite (ACL):
Sina Zarrieß, M. Soledad López Gambino, and David Schlangen. 2017. Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images. In Proceedings of the 10th International Conference on Natural Language Generation, pages 72–73, Santiago de Compostela, Spain. Association for Computational Linguistics.
Cite (Informal):
Refer-iTTS: A System for Referring in Spoken Installments to Objects in Real-World Images (Zarrieß et al., INLG 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/W17-3509.pdf