Abstract: A network that establishes a telephone call between a calling party and a called party and alters speech signals generated by the calling party during the telephone call. The network includes a network node that is coupled to the transmit channel of the calling party and the receive channel of the called party. The network node is programmed to receive a request to establish the telephone call from the calling party and receive a selection of a speech signal alteration from the calling party. The network node initiates the telephone call to the called party. Further, the network node alters the speech signal of the calling party based on the speech signal alteration selection.

Abstract: A method and apparatus for delivering personalized broadcast messages is disclosed. In accordance with one embodiment of the present invention, a broadcast message that is to be delivered to several recipients is stored in a network broadcast message database. Access numbers for each intended recipient of the broadcast message are stored in a recipient database in the network. The sender of the broadcast message generates a personalized message for each intended recipient and stores each personalized message in the recipient database. A message delivery module in the network retrieves the access number for each intended recipient from the recipient database and establishes a communications connection with each intended recipient. The message delivery module also retrieves the stored personalized message that is associated with the intended recipient and the stored broadcast message from the broadcast message database.

Abstract: The present invention relates to a method and apparatus for placing a message in digital data. The message is placed by manipulating certain data bits in a way that does not severely corrupt the data. The data can be mu-law encoded, wherein a value of 1 is assigned to one representation of zero, and a value of 0 is assigned to the other representation of zero. In this case, a message is placed in the data using these assigned values of 1 and 0.

Abstract: A system and method for delivering automated pre-recorded messages to intended recipients is disclosed. An automated call controller places phone calls to intended recipients and plays a pre-recorded message for the recipient after the call is answered. The automated call controller accesses phone numbers for intended recipients from a database and automatically dials the accessed phone numbers. The automated call controller monitors parameters associated with the telephone call. A message delivery decision model analyzes these monitored parameters, and any other parameters input to the decision model, and, based on the analysis of the parameters, optimizes the delivery of the pre-recorded message by the call controller. Results from the completed phone call are stored in the database and are utilized by the decision model to optimize the completion of future phone calls to that particular phone number.

Abstract: A system inserts one or more background sounds in a telephone call between a calling party and a called party. The system includes a network node coupled to a first telephone used by the calling party and a second telephone used by the called party. The network node is further coupled to an audio source. One or more background sounds are stored on the audio source. The calling party dials into the network node. The network node presents a menu of background sounds to the calling party who selects at least one background sound. The calling party then enters the phone number of the called party. The network node initiates the telephone call to the called party over a first telephone channel, and then inserts the selected background sound retrieved from the audio source onto the telephone channel. If a multi-party call is requested by the calling party, the calling party can select different background sounds that are inserted by the network node onto the telephone channel for each called party.

Abstract: A method and apparatus for recognizing an identifier entered by a user. A caller enters a predetermined identifier through a telephone handset. A signal representing the entered identifier is transmitted to a remote recognizer, which responds to the signal by producing a recognized output intended to match the entered identifier. The present invention compares this recognized identifier with a list of valid reference identifiers to determine which one of these reference identifiers most likely matches the entered identifier. In performing this determination, the present invention employs a confusion matrix, which is an arrangement of probabilities that indicate the likelihood that a given character in a particular character position of the reference identifier would be recognized by the recognizer as a character in the corresponding character position of the recognized identifier.

Abstract: An apparatus and method for the robust recognition of speech during a call in a noisy environment is presented. Specific background noise models are created to model various background noises which may interfere in the error free recognition of speech. These background noise models are then used to determine which noise characteristics a particular call has. Once a determination has been made of the background noise in any given call, speech recognition is carried out using the appropriate background noise model.

Abstract: In a speaker verification system, a method of compensating for differences in speech samples obtained during registration and those obtained during verification due to the use of different types of microphones is provided by filtering at least one of the samples such that the similarities of the two samples are increased. The filtered sample is used within the speaker verification matching process. A two-way comparison is disclosed in which both a verification speech sample and a reference sample are filtered with nonlinear microphone characteristics such as carbon microphone characteristics. A four-way comparison is also disclosed in which patterns produced from unfiltered verification and reference samples and patterns produced from the filtered verification and reference samples are compared to identify a match. A score is determined for each comparison. The comparison having the best score is used to determine if a match has occurred.

Abstract: A directional microphone assembly is constructed from a first-order-gradient microphone element enclosed within a housing, molded from an acoustically-opaque, resilient material such as Ethylene-Propylene-Diene-Monomer. The microphone element includes a diaphragm which moves under the influence of sound pressures applied on its opposite surfaces to generate an electrical signal which is proportional to the differential sound pressure. The housing includes a first acoustically-transparent channel for communicating sound pressure from a first opening in the housing to one surface of the diaphragm, and a second acoustically-transparent channel for communicating sound pressure from a second opening in the housing to the other surface of the diaphragm. The housing supports the microphone element and forms a continuous seal around its perimeter so that sound pressure in one channel does not leak into the other.

Abstract: An apparatus and method for the robust recognition of speech during a call in a noisy environment is presented. Specific background noise models are created to model various background noises which may interfere in the error free recognition of speech. These background noise models are then used to determine which noise characteristics a particular call has. Once a determination has been made of the background noise in any given call, speech recognition is carried out using the appropriate background noise model.