Carnegie Mellon University
Browse

A keyword search system using open source software

Download (239.98 kB)
journal contribution
posted on 2014-12-01, 00:00 authored by Jan Trmal, Guoguo Chen, Dan Povey, Sanjeev Khudanpur, Pegah Ghahremani, Xiaohui Zhang, Vimal Manohar, Chunxi Liu, Aren Jansen, Dietrich Klakow, David Yarowsky, Florian MetzeFlorian Metze

Provides an overview of a speech-to-text (STT) and keyword search (KWS) system architecture build primarily on the top of the Kaldi toolkit and expands on a few highlights. The system was developed as a part of the research efforts of the Radical team while participating in the IARPA Babel program. Our aim was to develop a general system pipeline which could be easily and rapidly deployed in any language, independently on the language script and phonological and linguistic features of the language.

History

Publisher Statement

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Date

2014-12-01

Usage metrics

    Categories

    Keywords

    Kaldispoken term detectionkeyword searchspeech recognitiondeep neural networkspitchIARPA BABELOpenKWSInformation and Computing Sciences not elsewhere classified

    Licence

    In Copyright

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC