A method for N-best search for continuous speech recognition with limited storage space includes the steps of Viterbi pruning word level (same word, different time alignment, thus non-output differentiation) states and keeping the N-best sub-optimal paths for sentence level (output differentiation) ...http://www.google.com.tw/patents/US6374220?utm_source=gb-gplus-share專利 US6374220 - N-best search for continuous speech recognition using viterbi pruning for non-output differentiation states
