@InProceedings{serriere-EtAl:2016:COLING,
  author    = {Serri\`{e}re, Guillaume  and  Cerisara, Christophe  and  Fohr, Dominique  and  Mella, Odile},
  title     = {Weakly-supervised text-to-speech alignment confidence measure},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {2042--2050},
  abstract  = {This work proposes a new confidence measure for evaluating text-to-speech
	alignment systems outputs, which is a key component for many applications, such
	as semi-automatic corpus anonymization, lips syncing, film dubbing, corpus
	preparation for speech synthesis and speech recognition acoustic models
	training. This confidence measure exploits deep neural networks that are
	trained on large corpora without direct supervision. It is evaluated on an
	open-source spontaneous speech corpus and outperforms a confidence score
	derived from a state-of-the-art text-to-speech aligner. We further show that
	this confidence measure can be used to fine-tune the output of this aligner and
	improve the quality of the resulting alignment.},
  url       = {http://aclweb.org/anthology/C16-1192}
}