Foreign Language Analysis and Recognition (FLARe)

Abstract

This final technical report provides research results in the areas of Automatic Speech Recognition (ASR) and Information Retrieval (IR). Hybrid Deep Neural Network (DNN) Hidden Markov Model (HMM) systems were developed using i-vector input. An English ASR system was developed for the International Workshop on Spoken Language Translation (IWSLT) 2015 evaluation. ASR systems were developed for Arabic, Chinese, Farsi, Russian, and Ukrainian.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 08, 2016
Accession Number
AD1026646

Entities

People

  • Brian M. Ore
  • David M. Hoeferlin
  • Eric G. Hansen
  • Raymond E. Slyh
  • Stephen A. Thorn

Organizations

  • SRA International Inc

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Automated Speech Recognition
  • Computational Science
  • Computer Science
  • Computers
  • Foreign Languages
  • Hidden Markov Models
  • Information Retrieval
  • Language
  • Language Translation
  • Machine Translation
  • Markov Models
  • Natural Language Processing
  • Neural Networks
  • Probability
  • Recognition
  • Recurrent Neural Networks

Readers

  • Computational Linguistics
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation