| 主权项 |
1. A semiconductor integrated circuit device comprising:
a signal processing unit extracts frequency components of an inputted voice signal, and generates a feature pattern representing a state of distribution of the frequency components of the voice signal; a voice recognition database storage unit which stores a plurality of voice recognition databases each including a standard pattern representing a state of distribution of frequency components of plural phonemes used in a predetermined language, each of the plurality of voice recognition databases having been generated based on voice signals of a different group of speakers, each different group of speakers having a different age and/or gender than other ones of the groups of speakers; a conversion list storage unit which stores a conversion list expressed by character data and including plural words or sentences to be conversion candidates, the plural words or candidates being expected responses to a question or message; a standard pattern extraction unit which extracts the standard pattern corresponding to the character data representing the first syllable of each word or sentence included in the conversion list, from the voice recognition database; and a matching detection unit which receives an input of age and/or gender of a user, and selects a corresponding one of the plurality of voice recognition databases based on the input, and which compares the feature pattern generated from the first syllable of the voice signal with the standard pattern extracted by the standard pattern extraction unit, thus detects the matching of the syllable, and outputs information specifying a word or sentence that has the matching-detected syllable as the first syllable thereof. |
