대한음성학회:학술대회논문집 (Proceedings of the KSPS conference)
- 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
- /
- Pages.327-329
- /
- 2007
FSN 기반의 대어휘 연속음성인식 시스템 개발
Development of FSN-based Large Vocabulary Continuous Speech Recognition System
- Park, Jeon-Gue (Speech/Language Information Research Center, ETRI) ;
- Lee, Yun-Keun (Speech/Language Information Research Center, ETRI)
- 발행 : 2007.05.18
초록
This paper presents a FSN-based LVCSR system and it's application to the speech TV program guide. Unlike the most popular statistical language model-based system, we used FSN grammar based on the graph theory-based FSN optimization algorithm and knowledge-based advanced word boundary modeling. For the memory and latency efficiency, we implemented the dynamic pruning scheduling based on the histogram of active words and their likelihood distribution. We achieved a 10.7% word accuracy improvement with 57.3% speedup.
키워드