Microsoft Technology Licensing, LLC

David Gareth Ollason

Siddharth Bhatia

Yun-Cheng Ju

Daniel Herron

Kuansan Wang

Tal Saraf

Julian James Odell

William Folwell Barton

Stephen Frederick Potter

Michelle S Spina

Steve Sung-Nam Chang

A voice user interface authoring tool is configured to use categorized example caller responses, from which callflow paths, automatic speech recognition, and natural language processing control files can be generated automatically within a single, integrated authoring user interface. A voice user interface (VUI) design component allows an author to create an application incorporating various types of action nodes, including Prompt/Response Processing (PRP) nodes. At runtime, the system uses the information from each PRP node to prompt a user to say something, and to process the user's response in order to extract its meaning. An Automatic Speech Recognition/Natural Language Processing (ASR/NLP) Control Design component allows the author to associate sample inputs with each possible meaning, and automatically generates the necessary ASR and NLP runtime control files. The VUI design component allows the author to associate the appropriate ASR and NLP control files with each PRP node, and to associate an action node with each possible meaning, as indicated by the NLP control file.

Voice user interface authoring tool

A follow-up call to a user is made after completion of a first call with a voice user interface module operable on a computer. The voice user interface module inquiries about information communicated in the first call.

Automated follow-up call in a telephone interaction system

A process for collecting the identity of a telephone caller is disclosed. In one embodiment, a personalized Context Free Grammar (CFG) is created for each potential call recipient, and is configured to support identification of incoming callers utilizing voice recognition. Each CFG incorporates an indication of high probability callers and probability weights in each CFG are altered accordingly. When a recipient receives a call, the relevant CFG is applied in association with a voice recognition application to enable at least a preliminary identification of the caller. In accordance with another embodiment, the caller confirms identifications. In accordance with one embodiment, standard caller-ID functionality is utilized if possible at least to assist in the caller identification process. In accordance with still another embodiment, voice recognition enhanced caller identification is utilized to provide intelligent call routing functionality.

Speech recognition enhanced caller identification

Monitoring a spoken-word audio stream for a relevant concept is disclosed. A speech recognition engine may recognize a plurality of words from the audio stream. Function words that do not indicate content may be removed from the plurality of words. A concept may be determined from at least one word recognized from the audio stream. The concept may be determined via a morphological normalization of the plurality of words. The concept may be associated with a time related to when the at least one word was spoken. A relevance metric may be computed for the concept. Computing the relevance metric may include assessing the temporal frequency of the concept within the audio stream. The relevance metric for the concept may be based on respective confidence scores of the at least one word. The concept, time, and relevance metric may be displayed in a graphical display.

Concept monitoring in spoken-word audio

A speech recognition application including a recognition module configured to receive input utterances and an application module configured to select a recognition from the speech recognition module using output from a first iteration to select a recognition result for a second iteration. In one embodiment, the application module eliminates a previous rejected recognition result or results from the N-Best list for recognition. In another embodiment, the application module rescores N-Best entries based upon N-Best lists or information from another iteration. In another illustrated embodiment, the application module uses a limited grammar from a current N-Best list for subsequent recognition, for example for rerecognition using a recorded input from a previous iteration.

Speech recognition application or server using iterative recognition constraints

A method of generating an optimized grammar, for use in speech recognition, from a data set or big list of items, is disclosed. The method includes the steps of obtaining a tree representing items in the data set, and generating the grammar using the tree. The tree or tree data structure representing items in the data set is a simulated recognition search tree, representing items in the data set, which can be automatically generated from the data set.

Method and apparatus for automatic grammar generation from data entries

A method of providing information to a user in a telephone interactive system includes receiving a new call. A comparison is then made between an identifier associated with the new call with stored call information pertaining to previous calls. If the identifier associated with the new call matches an identifier associated with a previous call, a subsequent action taken in the new call is based on context information stored from the previous call.

Context retention across multiple calls in a telephone interaction system

A method of querying a user to select from a list in a voice-activated command system is provided. The method includes generating command prompt phrases during which the user can select items on the list. The command prompt phrases include an item on the list and an index for another item on the list. In some embodiments, each command prompt phrase also includes a period of silence between item on the list and the index for another item on the list. If a user selecting barge-in is received during a particular command prompt phrase, the corresponding item on the list is selected.

Method and apparatus for robustly locating user barge-ins in voice-activated command systems

A method of providing voice dialing assistance includes providing a first input to a speech recognition engine, with the first input corresponding to a speech sample provided by a caller attempting to reach an intended call recipient. A speech recognition output is generated in response to the first input. A potential call recipient is identified based upon the speech recognition output. A confirmation that the potential call recipient is the intended call recipient is implemented using a personal recording made by the potential call recipient.

Method and apparatus to improve name confirmation in voice-dialing systems

A method of executing operations in a voice-activated command system includes automatically initiating execution of a default operation. A user is then prompted, after the default operation has been initiated, to determine whether the user wishes to execute a second operation instead of the default operation. If the user wishes to execute the second operation instead of the default operation, execution of the default operation is terminated and execution of the second operation is initiated. In voice-activated and other command systems, such as voice dialing systems, this method allows the command system to execute the most probable operation without delay, while still making the system easily navigable by na&#xef;ve users. Systems, computer readable medium and apparatus which implement the methods of the present invention are also disclosed.

Method and apparatus for executing tasks in voice-activated command systems

A computer-implemented method is disclosed for creating a grammar to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms and identifying a set of terms that are pronounced the same but spelled differently. The method also includes placing a single term within the grammar to represent the set of terms.

Homonym processing in the context of voice-activated command systems

A method and system are provided for recognizing user input. User input is applied to at least one model to identify at least one decoded value found in a grammar. The decoded value and at least one database value stored in the grammar are then returned. The database value corresponds to a database value found in a database that is separate from the grammar. Under one embodiment, the database is associated with an application that accesses database values in the database. Under a further embodiment, two database values are returned with the decoded value where one of the database values corresponds to a database value in a first database and the other database value corresponds to a database value in a second database.

Method and architecture for consolidated database search for input recognition systems

A method is disclosed from constructing a grammar. The grammar is configured to be processed by a speech recognition engine in the context of a voice-activated command system. The method includes receiving a database containing a plurality of terms. From the plurality of terms, first and second terms are identified. The first and second terms are spelled differently but have a first pronunciation in common. One of the first and second terms also has a second pronunciation that is not inherent to the other of the first and second terms. The first and second pronunciations are placed within the grammar.

A method of facilitating interaction between a user and an automated system is provided. The method includes generating a graphical user interface on a display, with the graphical user interface inviting the user to provide an input to initiate execution of an operation. Upon receipt of an input from the user, a telephone call is automatically generated or initiated from the automated system to the user. The automated system can then prompt the user as required to execute the operation.

Growing community of inventors

Seattle, WA, United States of America

David Gareth Ollason