DMCA
Hybrid Language Models Using Mixed Types of Sub-lexical Units for Open Vocabulary German LVCSR
Cached
Download Links
| Citations: | 9 - 4 self |
BibTeX
@MISC{Ali_hybridlanguage,
author = {M. Ali and Basha Shaik and Amr El-desoky Mousa and Ralf Schlüter and Hermann Ney},
title = {Hybrid Language Models Using Mixed Types of Sub-lexical Units for Open Vocabulary German LVCSR},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
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. Index Terms: open vocabulary, morpheme, syllable, graphone 1.
Keyphrases
sub-lexical unit open vocabulary german lvcsr index term hybrid lm suitable word error rate mixed type natural choice language model normal graphemic morpheme open vocabulary traditional full-words system high degree broadcast news relative reduction inflected language large number large vocabulary continuous speech recognition political debate recognition lexicon open vocabulary lvcsr syllabic unit
