Abstract: Apparatus and method for operating a speech password system. The system apparatus records and stores a plurality of alphanumeric models. A user password is enrolled by the apparatus recognizing spoken sounds and comparing spoken password enrollment sounds with each of the alphanumeric models. Each user password is stored in the system by recording a pair of clusters identifying five alphanumeric models closest to and farther from the user spoken password enrollment sounds of the password. The system identifies subsequent passwords by recognizing a spoken access password and comparing the sounds thereof with each of the cluster identified alphanumeric models and assigning scores representing the similarity of the password access sounds with the alphanumeric models recorded in the pair of clusters. The spoken password access sounds are identified as a previously enrolled password by summarizing the cluster assigned scores and comparing the summation thereof with a predetermined threshold.

Abstract: Passwords are spoken by users and stored as speech models in a database. The database also contains a plurality of reference voice (RV) speech models based on speech inputs by various persons; each RV speech model includes characters, digits, or phrases comprising user assigned passwords. Preferably, a group of the RV speech models are selected based upon a predetermined level of difference between same and a speech model of the user's spoken password. In requesting access to the system, a user speaks the assigned password. The password entered by the user to obtain access is compared with user's own speech models and with the selected RV speech models to determine a measure of similarity. The validity of the password is determined based upon this measure of similarity.

Abstract: A voice capture system for use with a telephone switching system and transcribing terminals to record calling party generated information in predefined formats. The system digitizes and records messages generated by calling parties served by the telephone switching system and records recognized terminology occurring within the calling party voice messages as file records. The transcribing terminals are enabled to display the file record terminology in predefined formats and the recorded digitized calling party messages are transmitted as audio messages via a telephone coupled with the telephone switching system to operators of the transcribing terminals so that the operators may enter information contained within the recorded messages into the transcribing terminals to complete the predefined format that are subsequently recorded in the voice capture system.