This paper presents a new two-pass algorithm for Extra Large (more than 1M words) 
Vocabulary COntinuous Speech recognition based on the Information Retrieval (ELVIRCOS). 
The principle of this approach is to decompose a recognition process into two passes 
where the first pass builds the word subset for the second pass recognition. 
Word graph composition for continuous speech is presented. Experimental results 
for speech recognition system with vocabulary of about all words (approximately 2 M) are presented