Basavaraja, SV and Sreenivas, TV (2006) Low Complexity LID using Pruned Pattern Tables of LZW. In: 9th International Conference on Spoken Language Processing/INTERSPEECH 2006, 2006, 2006, Pittsburgh, PA, pp. 413-416.
fulltext.pdf - Published Version
Restricted to Registered users only
Download (148Kb) | Request a copy
We present two discriminative language modelling techniques for Lempel-Ziv-Welch (LZW) based LID system. The previous approach to LID using LZW algorithm was to directly use the LZW pattern tables forlanguage modelling. But, since the patterns in a language pattern table are shared by other language pattern tables, confusability prevailed in the LID task. For overcoming this, we present two pruning techniques (i) Language Specific (LS-LZW)-in which patterns common to more than one pattern table are removed. (ii) Length-Frequency product based (LF-LZW)-in which patterns having their length-frequency product below a threshold are removed. These approaches reduce the classification score (Compression Ratio [LZW-CR] or the weighted discriminant score [LZW-WDS]) for non native languages and increases the LID performance considerably. Also the memory and computational requirements of these techniques are much less compared to basic LZW techniques.
|Item Type:||Conference Paper|
|Additional Information:||Copyright for this article belongs to ISCA-International Speech Communication Association.|
|Keywords:||Language modelling; PRLM; LS-LZW; LF-LZW|
|Department/Centre:||Division of Electrical Sciences > Electrical Communication Engineering|
|Date Deposited:||08 Jan 2010 06:30|
|Last Modified:||19 Sep 2010 05:49|
Actions (login required)