@inproceedings{kafle-etal-2019-modeling,
title = "Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues",
author = "Kafle, Sushant and
Alm, Cissi Ovesdotter and
Huenerfauth, Matt",
editor = "Christensen, Heidi and
Hollingshead, Kristy and
Prud{'}hommeaux, Emily and
Rudzicz, Frank and
Vertanen, Keith",
booktitle = "Proceedings of the Eighth Workshop on Speech and Language Processing for Assistive Technologies",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1702",
doi = "10.18653/v1/W19-1702",
pages = "9--16",
abstract = "Prosodic cues in conversational speech aid listeners in discerning a message. We investigate whether acoustic cues in spoken dialogue can be used to identify the importance of individual words to the meaning of a conversation turn. Individuals who are Deaf and Hard of Hearing often rely on real-time captions in live meetings. Word error rate, a traditional metric for evaluating automatic speech recognition (ASR), fails to capture that some words are more important for a system to transcribe correctly than others. We present and evaluate neural architectures that use acoustic features for 3-class word importance prediction. Our model performs competitively against state-of-the-art text-based word-importance prediction models, and it demonstrates particular benefits when operating on imperfect ASR output.",
}
Markdown (Informal)
[Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues](https://aclanthology.org/W19-1702) (Kafle et al., SLPAT 2019)
ACL