Abstract: An automated telephone operator platform (e.g., an auto attendant) has a natural names library associated therewith. The natural names library comprises a large database of audio files representing common objects expected to be recognized by a telephone-based ASR application associated with or executing on the platform. Whenever the ASR application requires playback of an object file (e.g., a user's name associated with a mailbox), the system first determines whether the user has recorded a sample of his or her own voice. If so, the user's actual voice sample is output. If, however, the user's actual voice sample is not available or has not been recorded, the ASR application accesses the database to retreive objects files from which it then builds an appropriate output string.

Abstract: A toll call service center of the present invention is accessible by subscribers to a toll call service. One or more of the subscribers of the service have their own set of identifiers uniquely associated with a plurality of called stations desired to be accessed by the subscriber. The center comprises a voice command system having a storage for storing representations of the identifiers at storage locations uniquely identified with the subscriber. The command system also includes an announcing circuit and a processor operative under the control of a program stored therein. The processor is responsive to reception of an incoming call from a subscriber for controlling the announcing circuit to request the subscriber to speak an identifier associated with one of the plurality of called stations. A voice recognizer is responsive to receipt of the identifier for determining whether the identifier is valid.