Comverse, Inc.

Erin M Panttaja

Christopher M Schmandt

Lawrence A Denenberg

Marc J Neuberger

Marc D Tanner

Recognition of proper nouns by an automated speech recognition system is improved by augmenting the pronunciation of each proper noun or name in the natural language of the speech recognition system with at least one 'native' pronunciation in another natural language. To maximize recognition, preferably the pronunciations are predicted based on information not available to the speech recognition system. Prediction of pronunciation may be based on a location derived from a telephone number or postal address associated with the name and the language or dialect spoken in the country or region of that location. The 'native' pronunciation(s) may be added to a dictionary of the speech recognition system or directly to the grammar used for recognizing speech.

Recognition of proper nouns using native-language pronunciation

An interactive voice response system has speak-ahead capabilities similar to type-ahead IVR systems by determining multi-level grammars for responses. Preferably, an existing IVR application is processed automatically to generate a multi-level grammar database that can then be used in recognizing multi-level responses by a user.

Menu-based, speech actuated system with speak-ahead capability

A method and system for pronoun disambiguation adapts or learns from evaluating input by the user. The system stores pronoun information relating to pronoun usage for people, entities, and things that a user can use a pronoun to refer to in interacting with the system. The pronoun information is used by the system in a process that interprets the meaning of the pronoun in the context of the interaction with the user. The system and method include matching the pronoun reference input by the user to the likely person or thing based upon an evolving pronoun preference associated with the person, entity or thing. During each interaction, the system and method permit the user to verify that the system interpreted the pronoun as referring to the correct person, entity or thing and modifies the stored pronoun information to reflect the verified usage. The system and method can select pronoun preferences when a user adds an entry into their address book by searching for information that can indicate the proper pronoun preference for a given entry. The pronoun preference can be selected based upon information in the user's address book and/or other sources of pronoun information such as other users' address books and system databases.

Method and system for pronoun disambiguation

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.

Growing community of inventors

Somerville, MA, United States of America

Erin M Panttaja