Abstract: When an external terminal is signed on to a communications system, a voice link is set up between the external terminal and a teleworking subscriber line module of the communications system. Control information which is transferred in the form of DTMF signals from the external terminal via the voice link is converted at the teleworking subscriber line module into signaling information such as is usually available within the scope of a signaling protocol between internal terminals and the communications system.

Abstract: A voice verification system (1) has a verification server layer (55) providing centralized verification for multiple service providers in geographically spread locations. Each service provider has an IVR (41) using a C++ DLL API (43) to communicate with a verification server (56, 57) via ISPs (45) and a switching system (50). Each API (43) dynamically determines an optimum ISP/server socket to minimize a verification cycle time. The switching system (50) has a router and two-stage switch combination with firewalls to provide optimum resilience in paths to the server (56, 57).

Abstract: A method and apparatus for storing a voice message. The method includes the steps of storing a coded representation of the voice message in a block of memory associated with the voice message and sized to correspond to the size of the coded representation, retrieving the coded representation to play the voice message to a user, compressing the coded representation to produce a compressed representation of the voice message, the compressed representation having a lesser size than the coded representation, after the coded representation has been retrieved, and storing the compressed representation of the message in the block of memory in place of the coded representation.

Abstract: An announcement device in an electronic switching system is disclosed. It includes a virtual recorder in an electronic switching system. This allows for using a virtual channel for recording and monitoring voice announcements without occupying a system channel. The device includes a first switch highway (SHW) control section for controlling an announcement, a second SHW control section for controlling the announcement, a SHW channel for passing control signals of the first SHW control section and the second SHW control section, and a switch coupled to the SHW channel for performing an announcement. The first SHW control section and the second SHW control section perform address latching and data latching, respectively, for the announcement. The announcement device thus allows for a recording/monitoring service or a self loop-back test, without occupying a channel among the SHW channels performing announcement services.

Abstract: Methods and apparatus for processing at least one voice signal in which a centralized voice processing unit controls operation of a plurality of voice processing block. In a first embodiment, the centralized voice processing unit comprises a centralized voice activity detector that provides at least one voice activity indication to the plurality of voice processing blocks. In a second embodiment, the centralized voice processing unit comprises a centralized noise estimator that provides at least one noise estimate to the plurality of voice processing blocks. In a third embodiment, the centralized voice processing unit comprises a centralized signal characteristic estimator that provides at least one signal characteristic estimate to the plurality of voice processing blocks.

Abstract: Methods and apparatus for processing a transmitted voice signal include a centralized frame controller providing at least one boundary control signal to voice processing blocks and controlling the operation of the voice processing blocks on the transmitted voice signal based upon the boundary control signal.

Abstract: The lexical network of a large-vocabulary speech recognition system is structured to effectuate the rapid and efficient addition of words to the system's active vocabulary. The lexical network is structured to include Phonetic Constraint Nodes, which organize the inter-word phonetic information in the network, and Word Class Nodes which organize the syntactic semantic information in the network. Network fragments, corresponding to phoneme pronunciations and labeled to specify permitted interconnections to each other and to phonetic constraint nodes, are precompiled to facilitate the rapid generation of pronunciations for new words and thereby enhance the rapid addition of words to the vocabulary even during speech recognition. Functions defined in accordance with linguistic constraints may be utilized during recognition. Different language models and different vocabularies for different portions of a discourse may also be invoked depending, in part, on the discourse history.

Abstract: An advanced resource management system for an interactive voice response (IVR) service node allows multiple network ports to be served by one application port thereby increasing efficiency. An IVR with a plurality of network ports can now be efficiently configured with a plurality of application ports with varying capabilities. The resource management system determines which of the plurality of application ports on the service node has the capability to service an incoming call and then dynamically assigns a time slot to one of the network ports and to one of application ports to perform IVR services. The dynamic allocation of application ports to network ports also allows for a more simplified connection of the service node to the telecommunications network in which it is deployed.

Abstract: A telephone subscriber unit (22) includes a caller identification device (120), a memory unit (114), a pre-processor (124) and a text-to-speech synthesizer (TTS) (110). The caller identification device (120) receives caller ID information of a calling party in a first textual format and stores the caller ID information in the memory unit (114) The pre-processor (124) converts textual caller ID information from the first data format to a second data format suitable for text-to-speech synthesis by the text-to-speech synthesizer (110). The text-to-speech synthesizer (110) generates audible caller ID information responsive to receiving the textual caller information.

Abstract: Device and method of channel effect compensation for a telephone speech recognition system is disclosed. The telephone speech recognition system comprises a compensatory neutral network and a recognize. The compensatory neural network receives an input signal and compensates the input signal with a bias to generate an output signal. The compensatory neural network provides a plurality of first parameters to determine the bias. The recognizer is coupled to the compensatory neural network for classifying the output signal according to a plurality of second parameters in acoustic models to generate a recognition result and determine a recognition loss. The first parameters and second parameters are adjusted according to the recognition loss and an adjustment means during a training process.

Abstract: A server provides media and telephony services in a telecommunications network. The server has a distributed, object-oriented software architecture, allowing client applications to access resources located anywhere in the network. The server provides interfaces to media and telephony resources so that client applications, which may access the server through an IP data network, can access the resources. The software architecture framework is provided by Common Object Request Broker Architecture (CORBA). The interfaces provided by the server are Interface Definition Language (IDL) application program interfaces (APIs) implemented using a distributed object model such as CORBA.

Abstract: A call processing apparatus comprises a device for answering an incoming call, an interactive voice unit for eliciting information about the call from the customer, a device for analyzing the caller's response according to predetermined criteria to identify callers having certain behavioral characteristics, and a device for routing callers identified as having these characteristics to predetermined attendant stations. The apparatus therefore permits caller's having special needs to be automatically routed to suitably trained attendants.

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: System and method for deriving call routing information utilizing a network control data base system and voice recognition for matching spoken word sound patterns to routing numbers needed to set up calls. Public access is provided to a common database via a common access number or code. Terminating parties sponsor the call and originating parties need not be pre-subscribed to use the service. The common access number is used to initiate or trigger the service. The system advantageously operates under the direction of a service control point, which combines technologies for switching, interactive voice response, and voice recognition with the data base to automate the processes of assisting callers in making calls for which they do not know the phone number. Usage information is gathered on completed calls to each terminating party for billing. Three alternative deployments in the U.S.

Abstract: A PC-based PBX incorporating preexisting call control software designed to operate in a computing environment which is not PC-based. The PC-based PBX comprises a PC chassis; a PC motherboard within the chassis; a main PBX control card within the chassis for executing the preexisting call control software; a telecommunications card within the chassis and connected to the PBX main control card for implementing telephony communications with a public switched telephone network under control of the call control software; and a DSP card within the chassis and connected to the PBX main control card for implementing signaling and conferencing functions under control of the call control software.

Abstract: A system and method for recording the evidence of intent of a party to a transaction, archiving this speech recording, and notifying and making it available to interested parties. A party seeking an affirmation will send to the affirming party a communication outlining the terms of the affirmation to be made, and also a transaction identifier by which a system may identify the parties to the transaction. The affirming party communicates with the system. The affirming party communicates the transaction identifier, and subsequently recites a spoken affirmation which is recorded by the system. The system then stores the recording in association with a recording identifier which can be used later to retrieve the recording. Finally, the system communicates the recording identifier both to the affirming party and to the party requesting the affirmation. The requesting party is thus informed that the affirmation has been made.

Abstract: In accordance with a preferred embodiment of the present invention, there is provided a data processing system having a digital processor core, a dynamic RAM, which is preferably a synchronous, audio-grade RAM (SARAM) for speech and code storage, and a separate read-only memory (ROM) for storage of operation code for the DSP core. The system may also use SARAM having one area configured for code space and data, and a second, separate area, which can be used to encode or store speech. The system may also use either a boot mask ROM or erasable programmable ROM.

Abstract: A voice processing system comprising a digital trunk processor 135 and a system unit 145 incorporates a local voice recognition resource 185 provided on a digital signal processing board 180, and can access a remote voice recognition resource 320 in a server 300 via a local area network 250. The system provides a barge-in facility for the recognition resource on the remote server, whereby a prompt is played out to the user, and the incoming telephony signal is fed into a voice activity detector on the digital trunk processor. Responsive to a detection of incoming voice activity, the outgoing prompt is terminated, and the incoming data is transferred over the local area network to the remote server for recognition.

Abstract: A telephone and voice mail (voice processing) system is implemented using only a single processing means for controlling operations of both the telephone system and the voice mail system. The single processing means communicates with a hard disk, which stores programs for running the various operations of the system, voice prompts and all voice mail messages. The single processing means is coupled to signal processing circuitry, which emulates analog electronics that would be used for filters, tone decoder, generators, etc. The single processing means and signal processing circuitry are coupled to central office lines and station lines by a digital cross-point matrix, which can connect any voice path to another voice path. The system integrates call processing and voice processing into one system controlled by one set of software and a single processing means.

Abstract: The invention provided a a communication method, a voice transmission apparatus and a voice reception apparatus by which, in communication through a non-guarantee type network, deterioration in voice, unnatural interruption of language, jump of voice and so forth which arise from unstable communication or a load variation can be eliminated to the utmost to allow conversation which can be recognized readily and conversation by natural voice can be achieved. Voice of a talking person is inputted through a voice to electric conversion element such as a microphone to a voice inputting and outputting element, by which the voice signal is converted into a corresponding voice data electric signal. The voice data are inputted to a speech recognition and conversion section, by which they are converted into a character code data signal by speech synthesis.

Abstract: A method and apparatus for locating a desired record amongst a plurality of records in a telephone directory involves associating a frequency field with each of the records, the frequency field being operable to store a frequency metric. A characteristic field is also associated with each of the records, the characteristic field being operable to store a characteristic representation of at least one identifying characteristic of a rendering associated with the record. An input representation of a rendering purporting to identify the desired record is produced and the input representation is compared with the contents of the characteristic fields of at least some of the records and confidence metrics are assigned to the records respectively, each of the confidence metrics representing a respective probability that a respective record is the desired record. A determination is then made as to which of the records have the first and second highest confidence metrics.

Abstract: A method and an apparatus for implementing the method, which allow a transmitter (100) of a digital telecommunication system transmitting speech to transmit predetermined messages to a receiver (102) over a speech channel (108). Messages (114) are transmitted from the transmitter (100) to the receiver (102) on the speech channel (108) in such a way that they are encoded in some of the speech coding bits, whereby the speech coding bits selected for message transmission have been selected in such a way that they affect the quality of speech as little as possible. Most preferably, the speech coding bits used for transmitting messages are protected by channel coding (702, 704). Speech coding bits are “stolen” for message transmission only for very short periods at a time and only for exactly the time it takes to transmit the messages (114); at other times, the entire speech channel (108) is used normally for speech transmission.

Abstract: A telephony device includes a base station and a wireless handset. The base station has a responder with a memory. A processor of base station processes digital speech signals having a first code on signal lines connecting the input and output of the base station. The same processor also controls a converter which is located between the memory and the signal lines. Prior to storing in the memory, the converter codes the digital speech signals into a second code for storage in the memory, where the second code is the same code of the digital signals exchanged between the base station and the handset. Further, prior to reading from the memory, the converter decodes the digital speech signals of the second code stored in the memory into the first code.