| 摘要 |
In an apparatus for extracting information from an input speech signal, a preprocessor 41, a buffer 42, a segmenter 43, an acoustic classifier 45 and a feature extractor 47 are provided. The preprocessor 41 generates formant related information for consecutive time frames of the input speech signal. This formant related information is fed into buffer 42, which can store signals representative of a plurality of frames. The segmenter 43 monitors the signals representative of the incoming frames and identifies segments in the input speech signal during which variations in the formant related information remain within prespecified limits. The acoustic classifier 45 then determines classification information for each segment identified by the segmenter 43, based on acoustic classes found in training data. The feature estimator 47 then determines, for each segment, the information required, based on the input speech signal during that segment, training data and the classification information determined by the acoustic classifier 45. <IMAGE> |
