MPEG-7 audio LLD

Personal spoken sentence retrieval using two-level feature matching and MPEG-7 audio LLDs

FREE DOWNLOAD [PDF] PC Lin, JF Wang, JC Wang… – Journal of Information …, 2009
Conventional spoken sentence retrieval (SSR) relies on a large-vocabulary continuous- speech
recognition (LVCSR) system. This investigation proposes a feature-based speaker- dependent
SSR algorithm using two-level matching. Users can speak keywords as the query inputs