Requirements for the evaluation of computational speech segregation systems

    Research output: Contribution to journalJournal articleResearchpeer-review

    Abstract

    Recent studies on computational speech segregation reported improved speech intelligibility in noise when estimating and applying an ideal binary mask with supervised learning algorithms. However, an important requirement for such systems in technical applications is their robustness to acoustic conditions not considered during training. This study demonstrates that the spectro-temporal noise variations that occur during training and testing determine the achievable segregation performance. In particular, such variations strongly affect the identification of acoustical features in the system associated with perceptual attributes in speech segregation. The results could help establish a framework for a systematic evaluation of future segregation systems.
    Original languageEnglish
    JournalJournal of the Acoustical Society of America
    Volume136
    Issue number6
    Pages (from-to)398-404
    Number of pages7
    ISSN0001-4966
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    Dive into the research topics of 'Requirements for the evaluation of computational speech segregation systems'. Together they form a unique fingerprint.

    Cite this