International Business Machines Corporation

Nuance Communications, Inc.

Lenovo (singapore) Pte. Ltd.

Kohler Company

James Robert Lewis

Kerry Alan Ortega

Huifang Wang

Vanessa V Michelini

Barbara E Ballard

Ciprian Agapi

Ronald E Vanbuskirk

Wallace J Sadowski

Peeyush Jaiswal

Linda M Boyer

Raymond L Yee

Byron K Tiller

David J Allard

Ronald E VanBuskirk

Charles S Lanier

Debra A Johnson

Julie F Goodwin

Felipe Gomez

Arthur Keller

Francis James Canova, Jr

David E Reich

Margarita Zabolotskaya

Kimberlee A Kemble

William Villafana

Maria Elena Smith

Brent L Davis

Rajesh Balchandran

Brent D Metz

Melanie D Polkosky

Thomas A Kist

Ron Van Buskirk

William Kress Bodin

Thomas Edward Creamer

Fang Wang

Michael Peter Perrone

Girish Dhanakshirur

Amado Nassiff

Eugene Henry Ratzlaff

Leslie Robert Wilson

Gary Robert Hanson

Jayashree Subrahmonia

Matthew W Hartley

Patrick Michael Commarford

Bradley J DeBauche

Brent A Beatty

Sibyl C Sullivan

Daniel Ming-Te Hsieh

Peter Rowland Eastwood

Catherine Longenberger

David J Rasmussen

Jean Luter Stout

Connie Yudip Au

Cheryl A Kotan

Clifford J Strohofer

Hans Egger

Stephane Herman Maes

Charles Willard Cross, Jr

Frank Lawrence Jania

Mark Edward Epstein

Akram Bou-Ghannam

Peter J Kennedy

Walter Haenel

Shailesh B Gandhi

Jose L Rivero

Michael H Mirt

Andrew Simpson

Qing Gong

David Andrew Sawin

John Ferdinand Pitrelli

Jeffrey L Mueller

Ronald Van Buskirk

Michael H Ostrowski

Neal A Osborn

Wayne P Whitley

Robert Bedford Ferrier

Brenda Horowitz

Ji Wee Tan

Gary Joseph Pietrocarlo

Roger L Cox

Thomas T Murakami

James Christian Wulf

Russell Stephen Padgett

John H Schott

J Scott Gee

Ji Whee Tan

Oing Gong

Dominic Fischer

Michael Jacob

Danile M Hsieh

Dana L Vizner

Anthony F Corkell

C Thomas Rutherfoord

Stanley P Kaymen

Ronald E Van Buskirk

David F Ma

Julia E Maners

Debra Ann Johnson

Julie Francis Goodwin

David James Rasmussen

Byron Kevin Tiller

A method () and system () is provided to add the creation of examples at a developer level in the generation of Natural Language Understanding (NLU) models, tying the examples into a NLU sentence database (), automatically validating () a correct outcome of using the examples, and automatically resolving () problems the user has using the examples. The method () can convey examples of what a caller can say to a Natural Language Understanding (NLU) application. The method includes entering at least one example associated with an existing routing destination, and ensuring an NLU model correctly interprets the example unambiguously for correctly routing a call to the routing destination. The method can include presenting the example sentence in a help message () within an NLU dialogue as an example of what a caller can say for connecting the caller to a desired routing destination. The method can also include presented a failure dialogue for displaying at least one example that failed to be properly interpreted to ensure that ambiguous or incorrect examples are not presented in a help message.

Method and system for conveying an example in a natural language understanding application

A method () and system () is provided to add the creation of examples at a developer level in the generation of Natural Language Understanding (NLU) models, tying the examples into a NLU sentence database (), automatically validating () a correct outcome of using the examples, and automatically resolving () problems the user has using the examples. The method () can convey examples of what a caller can say to a Natural Language Understanding (NLU) application. The method includes entering at least one example associated with an existing routing destination, and ensuring an NLU model correctly interprets the example unambiguously for correctly routing a can to the routing destination. The method can include presenting the example sentence in a help message () within an NLU dialog as an example of what a caller can say for connecting the caller to a desired routing destination. The method can also include presented a failure dialog for displaying at least one example that failed to be properly interpreted to ensure that ambiguous or incorrect examples are not presented in a help message.

A method and system for defining standard catch styles used in generating speech application code for managing catch events, in which a style-selection menu that allows for selection of one or more catch styles is presented. Each catch style represents a system response to a catch event. A catch style can be selected from the style-selection menu. For each selected catch style, the system can prepare a response for each catch event. If the selected catch style requires playing a new audio message in response to a particular catch event, a contextual message can be entered in one or more text fields. The contextual message entered in each text field corresponds to the new audio message that will be played in response to the particular catch event. In certain catch styles, the entered contextual message is different for each catch event, while in other catch styles, the entered contextual message is the same for each catch event. Finally, if the selected catch style does not require playing of a new audio message in response to a particular catch event, the system can replay the system prompt.

Method and system for defining standard catch styles for speech application code generation

A computer-implemented method for dynamically generating a speech recognition grammar is provided. The method includes determining a target entry, and accessing a plurality of potential distracters. The method also includes selecting one or more distracters from the plurality of potential distracters. More particularly, each potential distracter selected is selected based upon an assessed acoustic dissimilarity between the distracter and the target entry. The method further includes dynamically generating a speech recognition grammar that includes the target entry and one or more of the distracters selected based upon an acoustic dissimilarity to the target entry.

Automatic generation of distractors for special-purpose speech recognition grammars

Embodiments of the present invention address deficiencies of the art in respect to interactive voice response (IVR) system session management and provide a method, system and computer program product for call interruption handling in an IVR data processing system. In an embodiment of the invention, a method for call interruption handling in an IVR data processing system can include detecting a call interruption of a telephone call between a caller and an IVR system during an established IVR session for the caller. The method also can include saving state information for the established IVR session in connection with the caller in response to detecting the call interruption.

Interactive voice response (IVR) system call interruption handling

A method for alleviating ambiguity issues of new user-defined speech commands. An original command for a user-defined speech command can be received. It can then be determined if the original command is likely to be confused with a set of existing speech commands. When confusion is unlikely, the original command can be automatically stored. When confusion is likely, a substitute command that is unlikely to be confused with existing commands can be automatically determined. The substitute can be presented as an alternative to the original command and can be selectively stored as the user-defined speech command.

Automatically providing a user with substitutes for potentially ambiguous user-defined speech commands

Embodiments of the present invention address deficiencies of the art in respect to interactive voice response (IVR) system session management and provide a method, system and computer program product for call interruption handling in an IVR data processing system. In an embodiment of the invention, a method for call interruption handling in an IVR data processing system can include detecting a call interruption of a telephone call between a caller and an IVR system during an established IVR session for the caller. The method also can include saving state information for the established IVR session in connection with the caller in response to detecting the call interruption. The method further can include determining a call back number for the caller and initiating a call back of the caller from the IVR system using the call back number of the caller thereby re-establishing an IVR session for the caller. Finally, the method can include restoring the saved state information for the re-established IVR session for the caller.

A method () in a speech recognition application callflow can include the steps of assigning () an individual option and a pre-built grammar to a same prompt, treating () the individual option as a valid output of the pre-built grammar if the individual option is a potential valid match to a recognition phrase () or an annotation () in the pre-built grammar, and treating () the individual option as an independent grammar from the pre-built grammar if the individual option fails to be a potential valid match to the recognition phrase or the annotation in the pre-built grammar.

Method and arrangement for managing grammar options in a graphical callflow builder

A method for automating an input process during a testing of a voice-enabled application so that a tester is not required to manually respond to each prompt of the voice-enabled application. The method including the step of identifying a session input store that includes input data associated with voice-enabled application prompts and the step of executing the voice-enabled application. The voice-enabled application can prompt for user input that is to be used when performing a speech processing task. Input data from the session input store can be automatically extracted responsive to the prompting and used in place of manually entered input. The speech processing service can perform the speech processing task based upon the extracted data.

Automating input when testing voice-enabled applications

A method for providing help within an interactive voice response application can include the step of determining an interactive voice response event corresponding to a help menu request. The event can be classified as a default help request or a user initiated help request. If the event is classified as a default help request, a time for receiving user input can be set to a default value. If, however, the event is classified as a user initiated help request, the time for receiving user input can be set to a value less than the default value. The interactive voice response application can take programmatic action upon expiration of the time for receiving user input.

Help option enhancement for interactive voice response systems

A prompt collecting tool () for an interactive voice response system () includes a voice enabled application server (), a voice simulator coupled to the voice enabled application server, and a processor coupled to the voice simulator. The processor can be programmed to execute () a voice application having a plurality of audio prompts, play () audio if a pre-stored audio is available for a particular prompt, capture () text when no pre-stored audio is available and forward () the captured text to the prompt collecting tool. The voice simulator can include a VoiceXML browser (), a text to speech text service (), and a text based recognition service () for example.

Method and system for collecting audio prompts in a dynamically generated voice application

A method of adjusting music length to expected waiting time while a caller is on hold includes choosing one or more media selections based upon their play duration and matching the selection(s) to the expected waiting time.

Adjusting music length to expected waiting time while caller is on hold

A method for alleviating ambiguity issues of new user defined speech commands. An original command for a user-defined speech command can be received. It can then be determined if the original command is likely to be confused with a set of existing speech commands. When confusion is unlikely, the original command can be automatically stored. When confusion is likely, a substitute command that is unlikely to be confused with existing commands can be automatically determined. The substitute can be presented as an alternative to the original command and can be selectively stored as the user-defined speech command.

A method, system and computer program for automatically generating call flow statistics in a voice application. Embodiments of the present invention address deficiencies of the art in respect to call flow statistics generation systems and provide a novel and non-obvious method, system and computer program product for automatically generating a call flow statistics-generating application and presenting updated statistics on a call flow representation. Various statistics collection points are identified on the visual representation. Upon running of the voice application, call flow statistics are gathered and presented for each statistics collection point. Call identifiers corresponding to each call path can be selected and call paths corresponding to the selected call identifier may be highlighted and their call statistics displayed.

Automatic generation of a callflow statistics application for speech systems

Growing community of inventors

Delray Beach, FL, United States of America

James Robert Lewis