DEVICE AND METHODS FOR SPEAKER-INDEPENDENT SPOKEN NAME SELECTION FOR TELECOMMUNICATIONS TERMINALS

摘要

The invention relates to a device and to methods for speaker-independent spoken name dialing for telecommunications terminals. One of the methods relates to the establishment of an individual name and telephone number directory for spoken name selection whilst the other relates to the carrying out of the spoken name dialing. The device has a memory (6) which is supplied with alphanumerically input user-defined names and associated telephone numbers. A grapheme-phoneme converter (8) produces a corresponding digital word model from an input name and said digital word model is stored together with the ASCII text or a code designated thereto in such a way that it can be accessed by a speech recognition device (7). The automatic spoken name dialing is carried out as follows: an acoustically input name is conveyed to the speech recognition device (7) in the form of a digital voice signal and the speech recognition device (7) compares this signal with the predetermined word models. The ASCII text corresponding to the word model which best matches the voice signal or the designated code is determined. Said ASCII text or code enables the associated telephone number to be called up from the memory (6). A telecommunications connection is then automatically established with this telephone number by the calling device (2) of the terminal.