@inproceedings{vasilescu-etal-2012-cross,
    title = "Cross-lingual studies of {ASR} errors: paradigms for perceptual evaluations",
    author = "Vasilescu, Ioana  and
      Adda-Decker, Martine  and
      Lamel, Lori",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/ingest-emnlp/L12-1134/",
    pages = "3511--3518",
    abstract = "It is well-known that human listeners significantly outperform machines when it comes to transcribing speech. This paper presents a progress report of the joint research in the automatic vs human speech transcription and of the perceptual experiments developed at LIMSI that aims to increase our understanding of automatic speech recognition errors. Two paradigms are described here in which human listeners are asked to transcribe speech segments containing words that are frequently misrecognized by the system. In particular, we sought to gain information about the impact of increased context to help humans disambiguate problematic lexical items, typically homophone or near-homophone words. The long-term aim of this research is to improve the modeling of ambiguous contexts so as to reduce automatic transcription errors."
}