NIPS Workshop: Advances in Acoustic Models

Ling Feng, Lars Kai Hansen

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

    171 Downloads (Pure)


    We discuss the cognitive components of speech at different time scales. We investigate cognitive features of speech including phoneme, gender, height, speaker identity. Integration by feature stacking based on short time MFCCs. Our hypothesis is basically ecological: we assume that features that essentially independent in a reasonable ensemble can be efficiently coded using a sparse independent component representation. This means that supervised and unsupervised learning should result in similar representations. We do indeed find that supervised and unsupervised learning of a model based on identical representations have closely corresponding abilities as classifiers.
    Original languageEnglish
    Publication date2006
    Publication statusPublished - 2006
    EventNIPS Workshop: Advances in Acoustic Models - Whistler, Canada
    Duration: 1 Jan 2006 → …


    ConferenceNIPS Workshop: Advances in Acoustic Models
    CityWhistler, Canada
    Period01/01/2006 → …


    • Unsupervised learning
    • Mixture of factor analyzers
    • Supervised learing
    • Feature stacking


    Dive into the research topics of 'NIPS Workshop: Advances in Acoustic Models'. Together they form a unique fingerprint.

    Cite this