• DocumentCode
    3698657
  • Title

    The extended longest common substring algorithm for spoken document retrieval

  • Author

    Dmitriy Prozorov;Alexandra Yashina

  • Author_Institution
    Vyatka State University, Kirov, Russia
  • fYear
    2015
  • Firstpage
    88
  • Lastpage
    90
  • Abstract
    The paper considers the spoken document retrieval problem. The proposed method uses a length of the longest common substring (LCS) algorithm for detection of query words. This method based on phoneme recognition of a spoken document. Also this method is compared with a text retrieval methods based on a vector space model. Use of a length of LCS and phoneme recognition improves retrieval effectiveness.
  • Keywords
    "Speech recognition","Hidden Markov models","Speech","Vocabulary","Text recognition","Weight measurement"
  • Publisher
    ieee
  • Conference_Titel
    Application of Information and Communication Technologies (AICT), 2015 9th International Conference on
  • Print_ISBN
    978-1-4673-6855-1
  • Type

    conf

  • DOI
    10.1109/ICAICT.2015.7338523
  • Filename
    7338523
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3698657