Helmholtz Gemeinschaft


Information theoretic based segments for language identification

Item Type:Article
Title:Information theoretic based segments for language identification
Creators Name:Harbeck, S. and Ohler, U. and Noth, E. and Niemann, H.
Abstract:In our paper we present two new approaches for language identification. Both of them are based on the use of so-called multigrams, an information theoretic based observation representation. In the first approach we use multigram models for phonotactic modeling of phoneme or codebook sequences. The multigram model can be used to segment the new observation into larger units (e.g. something like words) and calculates a probability for the best segmentation. In the second approach we build a fenon recognizer using the segments of the best segmentation of the training material as "words" inside the recognition vocabulary. On the OGI test corpus and on the NLST'95 evaluation corpus we got significant improvements with this second approach in comparison to the unsupervised codebook approach when discriminating between English and German utterances.
Source:Lecture Notes in Computer Science
Series Name:Lecture Notes in Computer Science
Title of Book:Text, Speech and Dialogue
Page Range:187-192
Official Publication:https://doi.org/10.1007/3-540-48239-3_34

Repository Staff Only: item control page

Open Access
MDC Library