Context-dependent error correction of spoken referring expressions

Ingrid Zukerman, Andisheh Partovi, Su Nam Kim

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    1 Citation (Scopus)

    Abstract

    We integrate a supervised machine learning mechanism for detecting erroneous words in the output of a speech recognizer with a two-tier error-correction approach that features (1) a noisy-channel model that replaces erroneous words with generic words, and (2) a phonetic-similarity mechanism that refines the generic words based on a short list of candidate interpretations. Our results, obtained on a corpus of 341 referring expressions, show that the first tier improves interpretation performance, and the second tier yields further improvements.
    Original languageEnglish
    Title of host publicationInterspeech 2015: Speech Beyond Speech
    EditorsSebastian Moller, Hermann Ney, Bernd Mobius, Elmar Noth, Stefan Steidl
    Place of PublicationBaixas France
    PublisherInternational Speech Communication Association (ISCA)
    Pages2032 - 2036
    Number of pages5
    Publication statusPublished - 2015
    EventAnnual Conference of the International Speech Communication Association (was Eurospeech) 2015 - Dresden, Germany
    Duration: 6 Sep 201510 Sep 2015
    Conference number: 16
    http://interspeech2015.org/

    Conference

    ConferenceAnnual Conference of the International Speech Communication Association (was Eurospeech) 2015
    Abbreviated titleInterspeech 2015
    CountryGermany
    CityDresden
    Period6/09/1510/09/15
    Internet address

    Cite this

    Zukerman, I., Partovi, A., & Kim, S. N. (2015). Context-dependent error correction of spoken referring expressions. In S. Moller, H. Ney, B. Mobius, E. Noth, & S. Steidl (Eds.), Interspeech 2015: Speech Beyond Speech (pp. 2032 - 2036). Baixas France: International Speech Communication Association (ISCA).
    Zukerman, Ingrid ; Partovi, Andisheh ; Kim, Su Nam. / Context-dependent error correction of spoken referring expressions. Interspeech 2015: Speech Beyond Speech. editor / Sebastian Moller ; Hermann Ney ; Bernd Mobius ; Elmar Noth ; Stefan Steidl. Baixas France : International Speech Communication Association (ISCA), 2015. pp. 2032 - 2036
    @inproceedings{c2c2a6963f4444ba88844d3b19d0c1cc,
    title = "Context-dependent error correction of spoken referring expressions",
    abstract = "We integrate a supervised machine learning mechanism for detecting erroneous words in the output of a speech recognizer with a two-tier error-correction approach that features (1) a noisy-channel model that replaces erroneous words with generic words, and (2) a phonetic-similarity mechanism that refines the generic words based on a short list of candidate interpretations. Our results, obtained on a corpus of 341 referring expressions, show that the first tier improves interpretation performance, and the second tier yields further improvements.",
    author = "Ingrid Zukerman and Andisheh Partovi and Kim, {Su Nam}",
    year = "2015",
    language = "English",
    pages = "2032 -- 2036",
    editor = "Sebastian Moller and Hermann Ney and Bernd Mobius and Elmar Noth and Stefan Steidl",
    booktitle = "Interspeech 2015: Speech Beyond Speech",
    publisher = "International Speech Communication Association (ISCA)",

    }

    Zukerman, I, Partovi, A & Kim, SN 2015, Context-dependent error correction of spoken referring expressions. in S Moller, H Ney, B Mobius, E Noth & S Steidl (eds), Interspeech 2015: Speech Beyond Speech. International Speech Communication Association (ISCA), Baixas France, pp. 2032 - 2036, Annual Conference of the International Speech Communication Association (was Eurospeech) 2015, Dresden, Germany, 6/09/15.

    Context-dependent error correction of spoken referring expressions. / Zukerman, Ingrid; Partovi, Andisheh; Kim, Su Nam.

    Interspeech 2015: Speech Beyond Speech. ed. / Sebastian Moller; Hermann Ney; Bernd Mobius; Elmar Noth; Stefan Steidl. Baixas France : International Speech Communication Association (ISCA), 2015. p. 2032 - 2036.

    Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

    TY - GEN

    T1 - Context-dependent error correction of spoken referring expressions

    AU - Zukerman, Ingrid

    AU - Partovi, Andisheh

    AU - Kim, Su Nam

    PY - 2015

    Y1 - 2015

    N2 - We integrate a supervised machine learning mechanism for detecting erroneous words in the output of a speech recognizer with a two-tier error-correction approach that features (1) a noisy-channel model that replaces erroneous words with generic words, and (2) a phonetic-similarity mechanism that refines the generic words based on a short list of candidate interpretations. Our results, obtained on a corpus of 341 referring expressions, show that the first tier improves interpretation performance, and the second tier yields further improvements.

    AB - We integrate a supervised machine learning mechanism for detecting erroneous words in the output of a speech recognizer with a two-tier error-correction approach that features (1) a noisy-channel model that replaces erroneous words with generic words, and (2) a phonetic-similarity mechanism that refines the generic words based on a short list of candidate interpretations. Our results, obtained on a corpus of 341 referring expressions, show that the first tier improves interpretation performance, and the second tier yields further improvements.

    UR - http://www.isca-speech.org/archive/interspeech_2015/papers/i15_2032.pdf

    M3 - Conference Paper

    SP - 2032

    EP - 2036

    BT - Interspeech 2015: Speech Beyond Speech

    A2 - Moller, Sebastian

    A2 - Ney, Hermann

    A2 - Mobius, Bernd

    A2 - Noth, Elmar

    A2 - Steidl, Stefan

    PB - International Speech Communication Association (ISCA)

    CY - Baixas France

    ER -

    Zukerman I, Partovi A, Kim SN. Context-dependent error correction of spoken referring expressions. In Moller S, Ney H, Mobius B, Noth E, Steidl S, editors, Interspeech 2015: Speech Beyond Speech. Baixas France: International Speech Communication Association (ISCA). 2015. p. 2032 - 2036