Special Feature

User Panel

My Panel

My Panel

Bookmark Science Articles

Recent News
Bookmark / Share This Science Site

Link-based feature extraction for model-based detection of echolocation calls.

Link-based feature extraction for model-based detection of echolocation calls. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

  • Abstract Text of This Paper
  • Journal Published
  • MeSH Keywords of This Abstract
  • Chemicals and Substances Used in this Paper
  • Grants and Granting Agency of this Research
  • Database Accession Numbers Used in this Paper
  • Related Papers
  • Related Research Tags
  • Rate this Research Paper
  • Link-based feature extraction for model-based detection of echolocation calls. Abstract Text:

    mark d skowronskiMark D Skowronski,m brock fentonM Brock Fenton,

    Frame-based acoustical analysis of echolocation calls from bats has recently been proposed to improve the robustness of automated call detection. Statistical models, popularized and honed by automated human speech processing research, learn the distributions of call features extracted identically from short overlapping frames of time. A fundamental assumption is that each frame contains at most one echolocation call. In field recordings of bats, this assumption is often violated by the presence of echoes and overlapping calls from multiple bats, which degrade automated detection performance. Simple rules, based on expert knowledge of echolocation calls, were used to follow local spectrogram ridges and to group ridge points into links. Frame-based features were extracted from the links, which may overlap in time, allowing links to be used in the existing model-based analysis paradigm. Improved performance using links is demonstrated for several pathological cases, including conspecific interaction and high-duty-cycle foraging.

    Link-based feature extraction for model-based detection of echolocation calls. Publishing Authors By Initials

    md skowronskiMD Skowronski,mb fentonMB Fenton,

    For similar abstracts research abstracts see: abstracts research

    PUBMED ID PMID:

    MEDLINE DATE:

    Link-based feature extraction for model-based detection of echolocation calls. Journal Published:

    PUBLICATION TYPE: Journal Article

    Journal: The Journal of the Acoustical Society of America

    VOLUME: 122

    Page Numbers: 2946

    Journal Abbreviation: J. Acoust. Soc. Am.

    ISSN: 1520-8524

    DAY: 14

    MONTH: Nov

    YEAR: 2007

    Link-based feature extraction for model-based detection of echolocation calls. Information

    Number of References:

    LANGUAGE: eng

    NlmUniqueID: 7503051

    Link-based feature extraction for model-based detection of echolocation calls. Keywords Mesh Terms:

    KEYWORDS:

    MESH TERMS:

    Chemical & Substance for Abstract: Link-based feature extraction for model-based detection of echolocation calls. Information

    Substance Name:

    Registry Number:

    Grant and Affiliation Information for Link-based feature extraction for model-based detection of echolocation calls.

    AFFILIATION: Biol., Univ. of Western Ontario, London ON N6A 5B7, Canada.

    Country: United States

    United States Research PublicationUnited States Research Publication

    AGENCY:

    GRANT:

    ACRONYM:

    MEDLINETA: J Acoust Soc Am

    REFSOURCE:

    DATABASENAME:

    ACCESSION NUMBER:

    Number Hits: 0

    Link-based feature extraction for model-based detection of echolocation calls Related Publications

     

    Molecular Station USER Menu

    Welcome to Molecular Station!

    You have to register before you can post on our forums or use our advanced features. Register Now! Its Free and Fast!

    Already registered? Login now below.

    User Name:

    Password:

    Already registered and Forgot your password? Click below to recover it.

    Recover Lost Password

    Join now - it's fast and free!

    Molecular Station is THE largest network of researchers, scientists and science lovers anywhere!

    Research Terms of Usage and Disclaimer
    Home
    Features

    Protocols

    DNA Forum

    Science Forum

    DNA Forum
    Biology Forum

    Science News


    [CaRP] XML error: Invalid document end at line 2

    For more click here:Science News