Statistical Analysis of the Relationship between Audio and Video speech parameters for Australian English

Roland Goecke, J Millar

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    Abstract

    After decades of research, automatic speech processing has become more and more viable in recent years. Audio-video speech recognition has been shown to improve the recognition rate in noise-degraded environments. However, which audio and video speech parameters to choose for an optimal system and how they are related is still an open research issue. Here we present a number of statistical analyses that aim at increasing our understanding of such audio-video relationships. In particular, we look at the canonical correlation analysis and the coinertia analysis which investigate the relationship of linear combinations of parameters. The analyses are performed on Australian English as an example.

    Original languageEnglish
    Title of host publicationAVSP 2003: ISCA Tutorial and Research workshop on audio visual speech processing
    EditorsJean-Luc Schwartz, David Sodoyer
    Place of PublicationCanada
    PublisherISCA
    Pages133-138
    Number of pages6
    Publication statusPublished - 2003
    EventAVSP 2003 - St Jorioz, France
    Duration: 4 Sep 20037 Sep 2003

    Conference

    ConferenceAVSP 2003
    CountryFrance
    CitySt Jorioz
    Period4/09/037/09/03

    Fingerprint Dive into the research topics of 'Statistical Analysis of the Relationship between Audio and Video speech parameters for Australian English'. Together they form a unique fingerprint.

  • Cite this

    Goecke, R., & Millar, J. (2003). Statistical Analysis of the Relationship between Audio and Video speech parameters for Australian English. In J-L. Schwartz, & D. Sodoyer (Eds.), AVSP 2003: ISCA Tutorial and Research workshop on audio visual speech processing (pp. 133-138). ISCA. https://www.isca-speech.org/archive_open/archive_papers/avsp03/av03_133.pdf