专利内容由知识产权出版社提供
专利名称：Segment-based similarity method for low
complexity speech recognizer
发明人：Philippe R. Morin,Ted H. Applebaum申请号：US09199721申请日：19981125公开号：US06230129B1公开日：20010508
专利附图：
摘要：A digital word prototype is constructed using one or more speech utterance fora given spoken word or phrase. First, a phone model is used to derive phoneme similaritytime series for each of a plurality of phonemes which represent the degree of similarity
between the speech utterance and a set of standard phonemes contained in the phonemodel. Next, the phoneme similarity data is normalized in relation to a non-speech partof the input speech signal. The normalized phoneme similarity data is divided intosegments, such that the sum of all normalized phoneme similarity values in a segmentare equal for each segment. Next, a word model is constructed from the phonemesimilarity data. To do so, within each segment, a summation value is determined bysumming over speech frames each of the normalized phoneme similarity valuesassociated with a particular phoneme. In this way, the word model is represented by avector of summation values that compactly correlate to the normalized phonemesimilarity data. Lastly, the results of the individually processed utterances for a givenspoken word (i.e., the individual word models) are combined to produce a digital wordprototype that electronically represents the given spoken word.
申请人：MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.
代理机构：Harness, Dickey & Pierce, P.L.C.
更多信息请下载全文后查看
