Abstract: A mobile device, such as a cellular telephone or a personal digital assistant (PDA), stores first personal data, such as any one or more of image, video, and audio data. The mobile device transmits the first personal data over a first wide area network (WAN) to a personal server.

Abstract: A mobile device, such as a cellular telephone or a personal digital assistant (PDA), stores first personal data, such as any one or more of image, video, and audio data. The mobile device transmits the first personal data over a first wide area network (WAN) to a personal server.

Abstract: A method for providing a bookmark in a voice application includes presenting the voice application to a user, allowing the user to access the voice application and provide vocal input to the voice application, creating, upon a user request, a bookmark to a location in the voice application in accordance with vocal input provided to the voice application, and providing the user with access to the bookmark in the voice application in order to return to the bookmarked location.

Abstract: Predicting speech recognizer confusion where utterances can be represented by any combination of text form and audio file. The utterances are represented with an intermediate representation that directly reflects the acoustic characteristics of the utterances. Text representations of the utterances can be directly used for predicting confusability without access to audio file examples of the utterances. First embodiment: two text utterances are represented with strings of phonemes and one of the strings of phonemes is transformed into the other strings of phonemes for a least cost as a confusability measure. Second embodiment: two utterances are represented with an intermediate representation of sequences of acoustic events based on phonetic capabilities of speakers obtained from acoustic signals of the utterances and the acoustic events are compared. Predicting confusability of the utterances according to a formula 2K/(T), K is a number of matched acoustic events and T is a total number of acoustic events.

Abstract: A personal server is provided for use with a mobile device, such as a cellular telephone. The personal server provides services to the user of the mobile device and to others authorized by the user, but to no other users. The personal server may be a home PC of the user of the mobile device. The personal server may serve as a proxy server for a shared server that provides services to the mobile device. The personal server may relay messages between the mobile device and the shared server. The personal server may store, log, filter, and perform other processing on the user's personal data, such as messages transmitted by the mobile device and/or the shared server. The personal server may aggregate messages received from a plurality of shared servers. A non-personal server may perform additional services, such as configuring the personal server and temporarily storing data if the personal server becomes inaccessible.

Abstract: An interactive voice response system is able to respond to questions from users on general topics by including words related to those topics in the grammar of a speech recognition system. Words that are added for all users are obtained from current news reports obtained from news providers accessible via the Internet, or a similar source. In addition, information is stored in an information database about places or people that may be of interest to users, such as weather reports and forecasts for many cities. The grammar of the speech recognition system is modified for an individual user to enable the system to recognize questions relating to, e.g., the weather in one of the cities, only when the system detects that the user has accessed a file containing a word included in the information database. The file may be a message, calendar or address book.

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 voice application platform receives information, such as a grammar and/or a prompt, from an application, which is indicative of the response(s) that the application expects. The voice application platform modifies the way the user can interact with the user interface and the application as a function of the expected responses. The voice application platform can provide a more consistent user interface by enabling the user to use terms or commands that the user is familiar with to interact with the application and the voice application platform performs the conversion between the user response and the response expected by the application in a manner transparent to the user and the application. The voice application platform can store information about the user and provide the appropriate information to the application (as requested) automatically based upon prior authorization from the user or by the voice application platform prompting the user on an as necessary basis.

Abstract: A method and system for providing a bookmark in a voice application is provided. The method generally includes allowing a user to access the voice application and provide input to the voice application; creating, upon a user request, a bookmark to a location in the voice application; and providing the user with access to the bookmark in the voice application in order to return to the bookmarked location. In one embodiment of the invention, creating a bookmark can include saving a pointer to the voice application; and saving a representation of vocal input by the user to the voice application up to the bookmarked location in the voice application, while providing the user with access to the bookmark location can include using the pointer to accessing the voice application; and replaying the representation of the interactions to progress through the voice page substantially up to the bookmarked location.

Abstract: Predicting speech recognizer confusion where utterances can be represented by any combination of text form and audio file. The utterances are represented with an intermediate representation that directly reflects the acoustic characteristics of the utterances. Text representations of the utterances can be directly used for predicting confusability without access to audio file examples of the utterances. First embodiment: two text utterances are represented with strings of phonemes and one of the strings of phonemes is transformed into the other strings of phonemes for a least cost as a confusability measure. Second embodiment: two utterances are represented with an intermediate representation of sequences of acoustic events based on phonetic capabilities of speakers obtained from acoustic signals of the utterances and the acoustic events are compared. Predicting confusability of the utterances according to a formula 2K/(T), K is a number of matched acoustic events and T is a total number of acoustic events.

Abstract: A voice-based interface method to provide user access to retrieve, sort, and navigate through messages in multiple media according to a plurality of message sorting criteria. A particular message may belong to multiple message lists and therefore can be heard in response to different queries. This method provides a consistent interface for navigating through the messages in each list of messages sorted by each criterion, proper insertion of newly arrived messages, and change of message status once the message has been heard.

Abstract: An interactive voice response system is able to respond to questions from users on general topics by including words related to those topics in the grammar of a speech recognition system. Words that are added for all users are obtained from current news reports obtained from news providers accessible via the Internet, or a similar source. In addition, information is stored in an information database about places or people that may be of interest to users, such as weather reports and forecasts for many cities. The grammar of the speech recognition system is modified for an individual user to enable the system to recognize questions relating to, e.g., the weather in one of the cities, only when the system detects that the user has accessed a file containing a word included in the information database. The file may be a message, calendar or address book.

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: 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.