Abstract: In a speech recognition system, a service processing center performs a service operation upon a speech recognition result and generates a speech response signal in accordance with the speech recognition result. A telephone terminal is connected via a telephone network to the service processing center. The telephone terminal receives a speech signal, recognizes the speech signal in accordance with a speech recognition software module, and acquires the speech recognition result. The speech recognition result is transmitted from the telephone terminal via the telephone network to the service processing center. The speech response signal is transmitted from the service processing center via the telephone network to the telephone terminal. The speech recognition software module is downloaded from the service processing center via the telephone network to the telephone terminal.

Abstract: A spoken user interface for speech-enabled devices includes a processor and a set of software instructions that are executable by the processor and stored in nonvolatile memory. A user of the speech-enabled device is prompted to enter a voice tag associated with an entry in a call history of the speech-enabled device. The call history includes lists of incoming and outgoing email messages, and incoming and outgoing telephone calls. The user is prompted to enter a voice tag after associated with a telephone number or email address in the call history after a user-selected number of telephone calls has been sent from the speech-enabled device to that telephone number, or has been sent from the telephone with that telephone number to the speech-enabled device, or after a user-selected number of email messages has been sent from the speech-enabled device to that email address, or has been sent from that email address to the speech-enabled device.

Abstract: A simplification of the process of developing call or dialog flows for use in an Interactive Voice Response system is provided. Three principal aspects of the invention include a task-oriented dialog model (or task model), development tool and a Dialog Manager. The task model is a framework for describing the application-specific information needed to perform the task. The development tool is an object that interprets a user specified task model and outputs information for a spoken dialog system to perform according to the specified task model. The Dialog Manager is a runtime system that uses output from the development tool in carrying out interactive dialogs to perform the task specified according to the task model. The Dialog Manager conducts the dialog using the task model and its built-in knowledge of dialog management. Thus, generic knowledge of how to conduct a dialog is separated from the specific information to be collected in a particular application.

Abstract: An advanced telecommunications system is provided for the recognizing of spoken commands over a cellular telephone, satellite telephone, or personal communications network. In the cellular application, for example, a Speech Recognition System interconnects either internally with or as an external peripheral to a cellular telecommunications switch. The Speech Recognition System includes an administrative subsystem, a call processing subsystem, a speaker-dependent recognition subsystem, a speaker-independent recognition subsystem, and a data storage subsystem. The Speech Recognition System also allows for increased efficiency in the cellular telephone network by integrating with the switch or switches as a shared resource. The administrative subsystem of the Speech Recognition System is used to keep statistical logs of pertinent call information. Pre-recorded instructional messages are stored in the memory of the call processing subsystem for instructing a user on his or her progress in using the system.

Abstract: Techniques for providing an automated conversational name dialing system for placing a call in response to an input by a user. One technique begins with the step of analyzing an input from a user, wherein the input includes information directed to identifying an intended recipient of a telephone call from the user. At least one candidate for the intended recipient is identified in response to the input, wherein the at least one candidate represents at least one potential match between the intended recipient and a predetermined vocabulary. A confidence measure indicative of a likelihood that the at least one candidate is the intended recipient is determined, and additional information is obtained from the user to increase the likelihood that the at least one candidate is the intended recipient, based on the determined confidence measure.

Abstract: A method and apparatus providing a telephone user with a manner in which to send DTMF commands during a call over a communication network by use of a speech-based user interface. The user speaks one or more words corresponding to DTMF commands, and the invention performs speech recognition on the spoken words, generates corresponding DTMF signals, and transmits the DTMF signals over the network.

Abstract: An apparatus and method is provided for placing a phone call when dialing out of the caller's local area. A database resident in a telephone connection mechanism contains the access codes required to place the out-of-local area call. A user input device is utilized by the calling party to retrieve the out-of-area access codes for the called party's telephone from the database. The user input device is also utilized by the calling party to input the called party's local telephone number into the telephone connection mechanism. The telephone connection mechanism automatically combines the local calling number input by the user with the out-of-area access codes retrieved from the database. The telephone connection mechanism then transmits a telephone connection request by utilizing the combined local telephone number and the out-of-area access codes.

Abstract: A method of and system for compressing and transmitting information which comprises recognizing a plurality of different types of information and providing a first representation of a recognized one of the plurality of different types of information having lower bandwidth transmission requirement than the recognized one of the plurality of different types of information. The first representation is transmitted to a remote receiver and a second representation of the recognized one of the recognized one of the plurality of different types of information at said remote receiver having greater information content than the first representation responsive to the first representation is provided. Responsive to the second representation, a recreation of the recognized one of the plurality of different types of information is provided. Recognizing includes providing a first data base and the second representation includes providing a second data base.

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: Telephone numbers are entered into an input device by a voice recognition method and apparatus. Location codes, such as country codes or area codes, can be generated by voice recognition of the area name. The method and apparatus also permit telephone numbers to be entered manually. This method of entering telephone numbers facilitates hands-free telephone calls in a vehicle.

Abstract: A method and apparatus providing a user interface within a phone that responds to a limited vocabulary of user trained voice commands. The interface allows users to perform all phone handset dialing functions using voice commands. Additionally, users will be able to create and modify entries within a voice recognition phonebook, whereby a number within the voice recognition phonebook can be called by saying the name associated with the number. The user interface provides a combination of voice and LCD displayed user prompts and responses to voice input. The interface responds to user voice commands and performs the command functions based upon matches to previously user trained voice command vocabulary words stored in memory.

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: The present invention a speech enabled automatic telephone dialer device uses a spoken name corresponding to name-telephone number data. User telephones are connected to a public service telephony mechanism. The telephony mechanism and user computer workstations containing loaded address book programs with name-telephone number data, are connected to the name dialer device. The name dialer device includes a host computer in a network; a telephony board for controlling the telephony mechanism for dialing; memory within the host computer for storing software and name-telephone number data; and, software to access computer-based address book programs, to receive voice inputs from the telephony mechanism, to create converted phonemes from names to match voice inputs with specific name-telephone number data from the computer-based address book programs for initiating an automatic dialing.

Abstract: A controllable toy system operative in conjunction with a household audio entertainment player, the system including a controllable toy, and an audio entertainment signal analyzer operative to analyze an audio entertainment signal so as to recognize therewithin predetermined audio entertainment elements and to command the controllable toy to perform at least one action according to the predetermined audio entertainment elements at a time corresponding to a time at which the audio entertainment elements are played by the household audio entertainment player.

Abstract: The present invention a speech enabled automatic telephone dialer device, system, and method using a spoken name corresponding to name-telephone number data of computer-based address book programs. The invention includes user telephones connected to a PBX-type telephony mechanism, which is connected to a telephony board of a name dialer device. User computer workstations containing loaded address book programs with name-telephone number data are connected to the name dialer device. The name dialer device includes a host computer in a network; a telephony board for controlling the PBX for dialing; memory within the host computer for storing software and name-telephone number data; and, software to access computer-based address book programs, to receive voice inputs from the PBX-type telephony mechanism, to create converted phonemes from names to match voice inputs with specific name-telephone number data from the computer-based address book programs for initiating an automatic dialing.

Abstract: The present invention is a speech enabled automatic name dialer dialing system for connection to a telephone system, utilizing a user computer having a computer-based address book program or equivalent name-telephone number data base for retrieval of name-telephone number data for creation of speech enabling phoneme sets for auto dialing by speaking a name, and utilizing telephone application programming interface, for use with a telephone systems having telephones with private branch exchanges. There is at least one user computer having a microphone and a speaker; a telephone application programming interface provider installed in the user computer; and at least one loaded address book program or equivalent name-telephone number data base contained in the user computer.

Abstract: An arrangement for allowing “hands-free” access to DTMF-controlled systems, such as one's voice mail messaging systems, utilizes a speech-to-DTMF tone application that monitors the communication between the user and the DTMF-controlled system. A speech recognition unit is utilized to retrieve certain voice commands (e.g., “next”, “skip”, “repeat”, “forward”, etc.) when uttered by the user. The application then translates the received commands into the proper DTMF tone sequence used by the DTMF-controlled system and transmits the DTMF tones to the system. The application is particularly useful in the cell phone environment and avoids the necessity of the user to constantly switch between using the keypad and listening to messages/commands from the system.

Abstract: A telecommunication network exchange and method of playing an announcement to a call party in a telephone exchange during connection set-up. The invention is based on the idea of totally separating the detection of the need for an announcement from playing the announcement. The need for the announcement is detected in a conventional manner at a given stage of call set-up. However, the exchange does not play the announcement immediately, but delays playing it up to a later stage of call set-up or up to a later event, if necessary. The announcement may be played, for example, not until collection of additional dialing is definitely terminated, the call is confirmed to be successful, the announcement is confirmed to be necessary/correct, and so on. As a consequence of the delayed playing of the announcement, wrong and unnecessary announcements and the failure of the call are thus avoided.

Abstract: A voice dialing method in a mobile telephone terminal. Upon reception of the dialing utterance, it is determined whether there are one or more pre-registered dialing utterances similar to an input dialing utterance within a first similarity value. If there are more than one dialing utterances within the first similarity value, it is determined whether there is a pre-registered dialing utterance similar to the input dialing utterance within a second similarity value higher than the first similarity value. If there is no dialing utterance within the second similarity value, names represented by the dialing utterances within the first similarity value are displayed. If a user selects one of the displayed names, a registered telephone number corresponding to the selected name is dialed. If there exists one dialing utterance within the second similarity value, a registered telephone number corresponding to the dialing utterance within the second similarity value is dialed.

Abstract: Speech recognition software in a telephone or telephone network recognizes a non-numeric word identifying a location, and a telephone number spoken by a user. The speech recognition grammar specifies locations and optionally constraints, such as the length, for telephone numbers in those locations. Locations may consist of countries, cities, communication network names, or any combination thereof. A database containing information about locations and telephone numbers may be used to determine whether the recognized telephone number could exist at the recognized location. Once an phone number has been identified, the user is asked to confirm the location and telephone number. If confirmed, an access code, country code or city code corresponding to the recognized location is dialed after a prefix, if needed, and is followed by the recognized telephone number. This is particularly useful for international locations to reduce the number of digits that must be recognized.

Abstract: An apparatus and method for processing voice labels and establishing communication connections between a calling party and a called party based on the voice labels. When the calling party wishes to establish a communication with the called party, the calling party activates his/her user device and speaks a voice label into the audio receiver of the user device. The calling party's voice is then converted into analog voice signals (or data voice signals if a data network is being used) and transmitted to a voice label processor. The voice label processor receives the voice signals and extracts at least one feature pattern from the voice signals that identifies the voice label to which it corresponds.

Abstract: A telecommunication system incorporates individual station instruments simplified by wireless operation, voice dialing, prepaid accounting and out-call operation, all enabled by cooperative system operation including supporting central equipment. Wireless operation of the central equipment involves a multiple port wireless platform along with other units for interfacing a multitude of mobile station instruments simultaneously for interactive audio communication to, regulate control, monitor and record operations of the instruments, and bridge communication with selected remote terminals through the public switched telephone network. Message capability, emergency abort to an operator station and security features supplement the basic system.

Abstract: A telecommunication system incorporates individual station instruments simplified by wireless operation, voice dialing, prepaid, and custom-programmed operating characteristics, all enabled by cooperative operation with supporting central equipment. Wireless operation of the central equipment involves a multiple port wireless platform along with other units for interfacing a multitude of mobile station instruments simultaneously for interactive audio communication to: program the operating characteristics as with respect to language, out call, anti-fraud, and available data, as well as to regulate, control, monitor, and record operations of the instruments, and bridge communication with selected remote terminals through the public switched telephone network. Message capability, rapid dialing, emergency abort to an operator station, and security features supplement the basic system.

Abstract: The present invention is a system that uses a limited text input entry device to narrow the possibilities for the selection of a phonetically based name used in a voice dialer. The user enters a DTMF signature of a name using only one key for each letter of the name. The signature is used by a dictionary to generate likely possibilities for the word. The user is asked whether the name is the name entered via playing the name to the user. If the user confirms the choice, the phonetic representation is stored along with a corresponding telephone number. If the played word does not match, a word generator generates additional likely possibilities from the signature. A speech recognizer picks the best representation from the dictionary and generator words based on a spoken version of the name. A first name and last name procedure, in which the first and last name signatures produce separate candidate lists, is used to provide an entry to an address book for voice dialing.

Abstract: A method is provided for enabling a user of a cellular radiotelephone (10) having a keypad (22) to assign selected speech utterances to keys 22a, 22b of the keypad 22. The method comprises the steps of: (a) prompting the user to depress at least one of the keys 22a, 22b; (b) in response to the user depressing at least one of the keys 22a, 22b, prompting the user to utter speech into a user-interface (19) of the radiotelephone (10) for assigning the speech to the depressed at least one key 22a, 22b; and (c) in response to the user uttering speech into the user-interface (19), storing the uttered speech in a memory (24) for identifying the depressed at least one key 22a, 22b with the uttered speech. Also in accordance with the invention, the user may dial a telephone number by simply uttering, into the user-interface (19), speech identifying those ones of the keys 22a, 22b which correspond to alpha-numeric characters of the telephone number.

Abstract: A call management system includes a local telephone circuit, a first telephone set, a second telephone set, and a telephony device. The first telephone set, the second telephone set, and the telephony device, each coupled to the local telephone circuit. The telephony device includes an off-hook monitor that detects an off-hook state on the local telephone circuit, and a command processor which recognizes a voice command signal transmitted from either the first telephone set or the second telephone set. A method for telephone call management is also disclosed.

Abstract: A portable radio telephone is provided with a headset having a user actuable switch and a microphone. The handset of the radio telephone includes circuitry for responding to the operation of the headset by the user to select or generate information such as a telephone number.

Abstract: Improved methods and arrangements are provided for use in a computer telephony system that supports dial by name operations. A multiple purpose contacts database is modified through a graphical user interface (GUI) to include corresponding phonetically spelled information and/or other alias information for a contact. Voice recognition capabilities in the computer telephony system, which support the dial by name operations, can be directly invoked through the GUI to playback the phonetically spelled information and/or other alias information.

Abstract: A voice activated dialing system includes a database maintaining a plurality of speech templates, associated telephone numbers, and recordings, wherein multiple speech templates can be linked to a single master recording. Processing circuitry compares an utterance from a user to one or more of the templates from the database to find a matching template. When a match is found, the processing circuitry retrieves the telephone number associated with the matching template and the corresponding recording. The recording is replayed to the user prior to initiating a connection to the associated telephone number. Master recordings can be used for multiple entries which are associated with a single telephone number to reduce storage requirements.

Abstract: A method for managing voice registration entries of voice recognition apparatus for use in both a handset and a hands-free kit. In the method, it is determined whether the handset is set to a hands-free mode where the handset is mounted on a cradle, thus connecting with the hands-free kit. If the handset is set to the hands-free mode, a voice registration entry for the handset is compared with a voice registration entry for the hands-free kit to calculate an entry difference value therebetween. A voice recognition process is performed, if the entry difference value is a minimum value, e.g., substantially zero. If the entry difference is larger than the minimum value, then a voice entry is registered for the hands-free kit, in response to a user confirmation. If the entry difference is smaller than the minimum value, then the voice entry is registered for the handset, in response to a user confirmation.

Abstract: A mobile telephone system and a method for answering a mobile telephone incoming call by a user's verbal command, to allow hands-free voice. The mobile telephone system includes a carkit and a mobile telephone. The mobile telephone has a programming key for pre-programming the user's voice greeting, a keypad for answering the call in telephone mode, a microphone for entering a user's verbal command for answering the call in carkit mode, a digital processor connected to the microphone for performing spectrum analysis and feature extractions of the user's verbal command in carkit mode, and a memory connected to the digital processor, having a database for storing the user's pre-programmed voice greeting digitized speech pattern. The pre-programmed voice greeting may be a factory-programmed voice greeting or the user's pre-programmed voice greeting, if previously initialized after pressing the programming key.

Abstract: In the method of the invention for dialling a telephone number by voice commands, the telephone number to be dialled can be uttered either as one or as several number strings or identifications, which are recognized in order to find out which number string or identification was uttered. An incorrectly recognized number string or identification will be marked incorrect.

Abstract: An automated hotel attendant is provided for coordinating room-to-room calling over a telephone switching system that supports multiple telephone extensions. A hotel registration system receives and stores the spelled names of hotel guests as well as assigns each guest an associated telephone extension. A lexicon training system is connected to the hotel registration system for generating pronunciations for each spelled name by converting the characters that spell those names into word-phoneme data. This word-phoneme data is in turn stored in a lexicon that is used by a speech recognition system. In particular, a phoneticizer in conjunction with a Hidden Markov Model (HMM) based model trainer serves as the basis for the lexicon training system, such that one or several HMM models associated with each guest name are stored in the lexicon.

Abstract: A telephone system for providing advanced telephony includes a first phone system adapter and a phone system controller. The first phone system adapter is coupled between a first telephone handset and a telephone line. Furthermore, the first phone system adapter is operable to (i) selectively couple the first telephone handset to the telephone line, (ii) receive an oral command from the first telephone handset when the first telephone handset is decoupled from the telephone line, and (iii) transmit the oral command to the phone system controller via the telephone line while the first telephone handset is decoupled from the telephone line. The phone system controller is coupled to the telephone line. Moreover, the phone system controller includes a personal computer system having an interactive phone system board and a computer readable medium.

Abstract: A wireless telephone system incorporates voice activated mobile instruments that are powered through a separate pod that includes electrical couplings either to A.C. structural power or D.C. vehicular power. Furthermore, the system accommodates both digital (DTMF) and voice (audio) communication from the keyless mobile instruments to and through a switched telephone network.

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: The apparatus comprises a data memory containing a series of correspondents' call numbers and, for each call number, at least one associated voice print; a sound transducer suitable for picking up the name of a desired corespondent as spoken by the user of the apparatus; voice recognition means suitable for analyzing the correspondent's name as picked up by the transducer and for transforming it into an associated voice print; selective memory addressing means including associative means suitable for finding a voice print in the memory corresponding to the print supplied by the voice recognition means, and in the event of a match, for addressing the corresponding memory position; and means co-operating with the associative means for applying the addressed call number to the radiotelephone circuits.

Abstract: A telephone announcement system 10 has a URL computer 30 that accesses announcements stored on Internet sites 41-44. Subscribers may enter the sites 41-44 to create or change announcements.

Abstract: A system and method for extracting key information from digitized audio messages, including telephone voice messages. Information, such as a telephone number and the name of the caller, is derived and extracted from a voice message and used to establish links to the information within the message. The telephone number and name of the caller can then be replayed without the need to replay the entire voice message. The telephone number and name of the caller can also be used as indices into an information database.

Abstract: A voice-dialing apparatus and method extracts semantic features from a speech signal and transmits a set of semantic feature characteristics over a telecommunication control channel to a remote speech recognition processor. Once received, the remote speech recognition processor uses the feature set to retrieve a name and number corresponding to the audio signal received from the user and to automatically dial the number for the user.

Abstract: A voice enhanced phone card which allows a caller to place a call by voice activated dialing only when the caller desires it is presented. A caller places a call using a standard calling card switch number and enters a predetermined service code. The voice enhanced phone card system recognizes the service code, and using known telephone switching capabilities, switches the call to a voice activated dialing system at a main feature point in the voice activated dialing system call flow. The call is then connected to a destination using the voice activated dialing routine.

Abstract: A system and method for allowing a communication device to accepts voice commands from a user. The voice commands can include commands to execute or dial key sequences or commands to control device functionality. Voice commands are received from a user of the communication device, indicating a command to be carried out by said communication device. The commands are interpreted and executed by the communication device.

Abstract: A system (8, 60, 500) for identifying an unidentified person (14, 510) includes a database (42) that contains utterance data (162) and an ambiguity-resolution criterion (114, 119, 121) corresponding to a known person. A processing system (10, 11, 502) is coupled to the database (42) and receives utterance information and an ambiguity-resolution identifier corresponding to the unidentified person (14, 510). The processing system (10, 11, 502) compares the utterance information with the utterance data (162) to identify the unidentified person (14, 510) as at least one known person. If the processing system (10, 11, 502) ambiguously identifies the unidentified person (14, 510) as more than one known person, the processing system (10, 11, 502) compares the ambiguity-resolution identifier with the ambiguity-resolution criterion (114, 119, 121) to identify the unidentified person (14, 510) as a particular known person.

Abstract: An external control unit (ECU) with a reduced keypad is tightly integrated in a voice activated vehicular telephone system which further includes a voice adapter (VA) providing an intelligent interface between the ECU and a portable telephone removably coupled to a portable telephone holder. By taking full advantage of the voice recognition capabilities of the VA, the ECU is able to effectively harness the extensive power of the vehicular telephone system while requiring a very small amount of vehicle space through the combination of an internal microphone and a keypad with a very few number of keys. The remaining keys are specifically chosen for their unique value in the integrated system and are further defined to support multiple mode-specific functions.