Approaches for Language Identification in Mismatched Environments

Abstract

In this paper, we consider the task of language identification in the context of mismatch conditions. Specifically, we address the issue of using unlabeled data in the domain of interest to improve the performance of a state-of-the-art system. The evaluation is performed on a 9-language set that includes data in both conversational telephone speech and narrowband broadcast speech. Multiple experiments are conducted to assess the performance of the system in this condition and a number of alternatives to ameliorate the drop in performance. The best system evaluated is based on deep neural network bottleneck features using i-vectors. The proposed system results in a 30% improvement over the baseline result.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 08, 2016
Accession Number
AD1033826

Entities

People

  • Gabriel Martinez-montes
  • Pedro A. Torres-carrasquillo
  • Shahan C. Nercessian

Organizations

  • MIT Lincoln Laboratory

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Department Of Defense
  • Dimensionality Reduction
  • Environment
  • Errors
  • Feature Extraction
  • Identification
  • Iterations
  • Language
  • Neural Networks
  • Recognition
  • Retraining
  • Standards
  • Training
  • United States
  • Unsupervised Machine Learning

Fields of Study

  • Computer science
  • Engineering

Readers

  • Neural Network Machine Learning.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks