@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://preview.aclanthology.org/iwcs-25-ingestion/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."
}