CONF Motlicek_ICASSP2010_2010/IDIAP Application of Out-Of-Language Detection To Spoken-Term Detection Motlicek, Petr Valente, Fabio https://publications.idiap.ch/index.php/publications/showcite/Motlicek_Idiap-RR-04-2010 Related documents 2010 IEEE International Conference on Acoustics, Speech and Signal Processing Dallas, USA 2010 April 2010 This paper investigates the detection of English spoken terms in a conversational multi-language scenario. The speech is processed using a large vocabulary continuous speech recognition system. The recognition output is represented in the form of word recognition lattices which are then used to search required terms. Due to the potential multi-lingual speech segments at the input, the spoken term detection system is combined with a module performing out-of language detection to adjust its confidence scores. First, experimental results of spoken term detection are provided on the conversational telephone speech database distributed by NIST in 2006. Then, the system is evaluated on a multi-lingual database with and without employment of the out-of-language detection module, where we are only interested in detecting English terms (stored in the index database). Several strategies to combine these two systems in an efficient way are proposed and evaluated. Around 7% relative improvement over a stand-alone STD is achieved REPORT Motlicek_Idiap-RR-04-2010/IDIAP Application of Out-Of-Language Detection To Spoken-Term Detection Motlicek, Petr Valente, Fabio EXTERNAL https://publications.idiap.ch/attachments/reports/2009/Motlicek_Idiap-RR-04-2010.pdf PUBLIC Idiap-RR-04-2010 2010 Idiap Rue Marconi 19, Martigny January 2010 This paper investigates the detection of English spoken terms in a conversational multi-language scenario. The speech is processed using a large vocabulary continuous speech recognition system. The recognition output is represented in the form of word recognition lattices which are then used to search required terms. Due to the potential multi-lingual speech segments at the input, the spoken term detection system is combined with a module performing out-of-language detection to adjust its confidence scores. First, experimental results of spoken term detection are provided on the conversational telephone speech database distributed by NIST in 2006. Then, the system is evaluated on a multi-lingual database with and without employment of the out-of-language detection module, where we are only interested in detecting English terms (stored in the index database). Several strategies to combine these two systems in an efficient way are proposed and evaluated. Around 7% relative improvement over a stand-alone STD is achieved.