Is Cognitive Activity of Speech Based On Statistical Independence?

Ling Feng, Lars Kai Hansen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    196 Downloads (Orbit)

    Abstract

    This paper explores the generality of COgnitive Component Analysis (COCA), which is defined as the process of unsupervised grouping of data such that the ensuing group structure is well-aligned with that resulting from human cognitive activity. The hypothesis of {COCA} is ecological: the essentially independent features in a context defined ensemble can be efficiently coded using a sparse independent component representation. Our devised protocol aims at comparing the performance of supervised learning (invoking cognitive activity) and unsupervised learning (statistical regularities) based on similar representations, and the only difference lies in the human inferred labels. Inspired by the previous research on COCA, we introduce a new pair of models, which directly employ the independent hypothesis. Statistical regularities are revealed at multiple time scales on phoneme, gender, age and speaker identity derived from speech signals. We indeed find that the supervised and unsupervised learning provide similar representations measured by the classification similarity at different levels.
    Original languageEnglish
    Title of host publicationProccedings of the 30th Meeting of the Cognitive Science Society (CogSci'08)
    PublisherCognitive Science Society
    Publication date2008
    Pages1197-1202
    ISBN (Print)978-0-9768318-3-9
    Publication statusPublished - 2008
    Event30th Meeting of the Cognitive Science Society - Washington, United States
    Duration: 23 Jul 200826 Jul 2008
    Conference number: 30

    Conference

    Conference30th Meeting of the Cognitive Science Society
    Number30
    Country/TerritoryUnited States
    CityWashington
    Period23/07/200826/07/2008

    Keywords

    • statistical regularity
    • classification
    • unsupervised learning
    • Cognitive component analysis
    • supervised learning

    Fingerprint

    Dive into the research topics of 'Is Cognitive Activity of Speech Based On Statistical Independence?'. Together they form a unique fingerprint.

    Cite this