Improvement of non-negative matrix factorization based language model using exponential models

M. Novak, R. Mammone

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

This paper describes the use of exponential models to improve non-negative matrix factorization (NMF) based topic language models for automatic speech recognition. This modeling technique borrows the basic idea from latent semantic analysis (LSA), which is typically used in information retrieval. An improvement was achieved when exponential models were used to estimate the a posteriori topic probabilities for an observed history. This method improved the perplexity of the NMF model, resulting in a 24% perplexity improvement overall when compared to a trigram language model.

Original languageEnglish (US)
Title of host publication2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages190-193
Number of pages4
ISBN (Electronic)078037343X, 9780780373433
DOIs
StatePublished - Jan 1 2001
EventIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Madonna di Campiglio, Italy
Duration: Dec 9 2001Dec 13 2001

Publication series

Name2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings

Other

OtherIEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001
CountryItaly
CityMadonna di Campiglio
Period12/9/0112/13/01

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Improvement of non-negative matrix factorization based language model using exponential models'. Together they form a unique fingerprint.

  • Cite this

    Novak, M., & Mammone, R. (2001). Improvement of non-negative matrix factorization based language model using exponential models. In 2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings (pp. 190-193). [1034619] (2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASRU.2001.1034619