Recent Improvements in Neural Network Acoustic Modeling for LVCSR in Low Resource Languages

Abstract

In this paper we focus on several techniques that improve deep neural network (DNN) acoustic modeling for low-resource languages. We explore the use of different features such as, fundamental-frequency variation (FFV), tonal features, and normalization of these features for deep neural network training. Specifically we study the impact of these features in conjunction with a tonal lexicon and several neural network architectures including hybrid and bottleneck feature-based configurations. We also explore the use of un-transcribed data and ways to balance it with transcribed data, to enhance the performance of the best performing LVCSR system. Results are presented in the context of the IARPA Babel program on development languages from Babel option period as well as on the surprise language from the base period of the program. We show that these improved methods can provide up to 15 percent relative reduction in WER and improvements in keyword search, in the languages explored under the BABEL program.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 14, 2014
Accession Number
AD1172406

Entities

People

  • Abhinav Sethy
  • Andrew Rosenberg
  • Bhuvana Ramabhadran
  • Brian Kingsbury
  • Jia Cui
  • Xiaodong Cui

Organizations

  • City University of New York
  • IBM Thomas J. Watson Research Center

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Automata Theory
  • Automated Speech Recognition
  • Computer Languages
  • Computer Science
  • Computers
  • Computing System Architectures
  • Department Of Defense
  • Dictionaries
  • Factor Analysis
  • Frequency
  • Information Science
  • Language
  • Markov Models
  • Models
  • Natural Language Processing
  • Network Architecture
  • Network Science
  • Neural Networks
  • Recognition

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Speech Processing/Speech Recognition.

Technology Areas

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