A voice-controlled, repertory-dialer system

This paper describes a speaker-trained, voice-controlled, repertory-dialer system that includes a real-time speech analyzer, an isolated-word recognizer, a voice-response system, and a simulated dialer. The system is implemented on a minicomputer with a high-speed array processor performing the real-time operations. The vocabulary consists of seven command words, ten digits, and any number of names up to a specified maximum. To train the system, the user speaks each vocabulary word twice to provide reference templates for the system. After training, the system can dial the telephone number corresponding to any name in the repertory, or it can dial a 4-digit telephone extension spoken as a string of isolated digits. The system operates in two modes. In the first (cued by a double beep), the user can modify the repertory either by adding or deleting names or by changing a phone number, or the user can enter the second mode using a specified command word. In the second mode (cued by a single beep), the user can speak any name in the repertory or can give a 4-digit telephone extension. The system was tested by six talkers (three male and three female, three of whom were naive and three experienced users) over a three-week period. A total of 4620 words were spoken, and during the course of the text there were no recognition errors. A request for a repeat of a spoken word occurred about 2 percent of the time.