Effect of pronunciations on OOV queries in spoken term detection

• Main Authors: Can, Dogan (Author), Cooper, Erica (Contributor), Sethy, Abhinav (Author), White, Chris (Author), Ramabhadran, Bhuvana (Author), Saraclar, Murat (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers, 2010-10-07T15:33:00Z.
• Subjects: Article
• Online Access: Get fulltext

 The spoken term detection (STD) task aims to return relevant segments from a spoken archive that contain the query terms whether or not they are in the system vocabulary. This paper focuses on pronunciation modeling for out-of-vocabulary (OOV) terms which frequently occur in STD queries. The STD system described in this paper indexes word-level and sub-word level lattices or confusion networks produced by an LVCSR system using weighted finite state transducers (WFST).We investigate the inclusion of n-best pronunciation variants for OOV terms (obtained from letter-to-sound rules) into the search and present the results obtained by indexing confusion networks as well as lattices. The following observations are worth mentioning: phone indexes generated from sub-words represent OOVs well and too many variants for the OOV terms degrade performance if pronunciations are not weighted.