2011 HybridLanguageModelsUsingMixedT

From GM-RKB
Jump to navigation Jump to search

Subject Headings: OOV Word; OOV Word Detection System; Open Vocabulary; Word Error Rate (WER); OOV Rate; Large Vocabulary Continuous Speech Recognition (LVCSR) System; Neural Network Language Model; Morpheme-based Subword Unit; Syllable-based Subword Unit; Graphone-based Sub-Word Unit.

Notes

Cited By

Quotes

Author Keywords

Abstract

German is a highly inflected language with a large number of words derived from the same root. It makes use of a high degree of word compounding leading to high Out-of-vocabulary (OOV) rates, and Language Model (LM) perplexities. For such languages the use of sub-lexical units for Large Vocabulary Continuous Speech Recognition (LVCSR) becomes a natural choice. In this paper, we investigate the use of mixed types of sub-lexical units in the same recognition lexicon. Namely, morphemic or syllabic units combined with pronunciations called graphones, normal graphemic morphemes or syllables along with full-words. This mixture of units is used for building hybrid LMs suitable for open vocabulary LVCSR where the system operates over an open, constantly changing vocabulary like in broadcast news, political debates, etc. A relative reduction of around 5.0% in Word Error Rate (WER) is obtained compared to a traditional full-words system. Moreover, around 40% of the OOVs are recognized.

References

BibTeX

@inproceedings{2011_HybridLanguageModelsUsingMixedT,
  author    = {M. Ali Basha Shaik and
               Amr El-Desoky Mousa and
               Ralf Schluter and
               Hermann Ney},
  title     = Hybrid Language Models Using Mixed Types of Sub-Lexical Units for
               Open Vocabulary German {LVCSR}},
  booktitle = {Proceeding of the 12th Annual Conference of the International Speech
               Communication Association (INTERSPEECH 2011)},
  pages     = {1441--1444},
  publisher = {ISCA},
  year      = {2011},
  url       = {http://www.isca-speech.org/archive/interspeech\_2011/i11\_1441.html},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2011 HybridLanguageModelsUsingMixedTM. Ali Basha Shaik
Amr El-Desoky Mousa
Ralf Schluter
Hermann Ney
Hybrid Language Models Using Mixed Types of Sub-Lexical Units for Open Vocabulary German {LVCSR}2011