DocumentCode :
3132578
Title :
Frame-based phonotactic Language Identification
Author :
Han, Ki Jin ; Pelecanos, Jason
Author_Institution :
IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
fYear :
2012
fDate :
2-5 Dec. 2012
Firstpage :
303
Lastpage :
306
Abstract :
This paper describes a frame-based phonotactic Language Identification (LID) system, which was used for the LID evaluation of the Robust Automatic Transcription of Speech (RATS) program by the Defense Advanced Research Projects Agency (DARPA). The proposed approach utilizes features derived from frame-level phone log-likelihoods from a phone recognizer. It is an attempt to capture not only phone sequence information but also short-term timing information for phone N-gram events, which is lacking in conventional phonotactic LID systems that simply count phone N-gram events. Based on this new method, we achieved 26% relative improvement in terms of Cavg for the RATS LID evaluation data compared to phone N-gram counts modeling. We also observed that it had a significant impact on score combination with our best acoustic system based on Mel-Frequency Cepstral Coefficients (MFCCs).
Keywords :
military computing; natural language processing; speech recognition; DARPA; Defense Advanced Research Projects Agency; MFCC; N-gram count modeling; RATS LID evaluation data; acoustic system; frame-based phonotactic language identification; frame-level phone log likelihoods; mel-frequency cepstral coefficients; phone N-gram events; phone recognizer; phone sequence information; robust automatic transcription; short-term timing information; speech program; Acoustics; Principal component analysis; Rats; Speech; Support vector machines; Timing; Vectors; DARPA RATS; language identification; phone event modeling with timing information; phonotactic;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Spoken Language Technology Workshop (SLT), 2012 IEEE
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4673-5125-6
Electronic_ISBN :
978-1-4673-5124-9
Type :
conf
DOI :
10.1109/SLT.2012.6424240
Filename :
6424240
Link To Document :
بازگشت