Design of Multi-Purpose Preprocessor for Keyword Spotting and Continuous Language Support in Korean

한국어 핵심어 추출 및 연속 음성 인식을 위한 다목적 전처리 프로세서 설계

  • Received : 2012.11.18
  • Accepted : 2012.12.05
  • Published : 2013.01.31


The voice recognition has been made continuously. Now, this technology could support even natural language beyond recognition of isolated words. Interests for the voice recognition was boosting after the Siri, I-phone based voice recognition software, was presented in 2010. There are some occasions implemented voice enabled services using Korean voice recognition softwares, but their accuracy isn't accurate enough, because of background noise and lack of control on voice related features. In this paper, we propose a sort of multi-purpose preprocessor to improve this situation. This supports Keyword spotting in the continuous speech in addition to noise filtering function. This should be independent of any voice recognition software and it can extend its functionality to support continuous speech by additionally identifying the pre-predicate and the post-predicate in relative to the spotted keyword. We get validation about noise filter effectiveness, keyword recognition rate, continuous speech recognition rate by experiments.