Elizabeth Roche

Bio: Elizabeth Roche is an academic researcher from Sprint Corporation. The author has contributed to research in topics: Session (computer science) & Input device. The author has an hindex of 9, co-authored 12 publications receiving 762 citations.

Method and system for enhanced response to voice commands in a voice command platform

Abstract: A method and system for responding to voice commands in a voice-command platform. The platform receives a voice command during a voice command session with a user, and the platform responsively carries out a set of system-level logic. For example, the platform may determine that the voice command is an alias-grammar (whether personal to a user, or global for the platform) and may then convert the alias-grammar into an actual grammar. As another example, the platform may determine that the voice command is a bookmark command, such as a request to save a given voice command navigation point in a centralized list of bookmarks for the user, or to recall a navigation point from the user's centralized list, and the platform may respond to the bookmark command accordingly. And as yet another example, the platform may recognize a voice command that is not defined by a voice command application currently being processed but that is instead defined globally for the voice command platform.

Voice browser with weighting of browser-level grammar to enhance usability

Abstract: A computer system in the form of a voice command platform includes a voice browser and voice-based applications. The voice browser has global-level grammar elements and the voice applications have application-level grammar and grammar elements. A programming feature is provided by which developers of the voice applications can programmably weigh or weight global-level grammar elements relative to the application-level grammar or grammar elements. As a consequence of the weighting, a speech recognition engine for the voice browser is more likely to accurately recognize voice input from a user. The weighting can be applied on the application as a whole, or at any given state in the application. Also, the weighting can be made to the global level grammar elements as a group, or on an individual basis.

Method for launching an electronic wallet

Abstract: A portable electronic device is disclosed The portable electronic device comprises a contactless communication transceiver configured to provide payment information to a point-of-sale terminal, a first input device configured to receive inputs, and a processor The first input device is selected from the group consisting of an accelerometer, a microphone, a camera, and a biometric sensor The processor is configured to activate an electronic wallet based on inputs from at least one of the first input device and the contactless communication transceiver, to access the payment information in the electronic wallet, and to provide the payment information to the contactless communication transceiver

Method and system for returning a call based on information in a voicemail message

Abstract: A method for returning a phone call based on information contained in a voicemail message. The method comprises receiving the voicemail message and applying service logic to analyze the voicemail message to extract a spoken phone number included in the voicemail message. The method further comprises associating the extracted phone number with the voicemail message and, in conjunction with retrieving the voicemail message, providing a recipient of the voicemail message with an option to dial the extracted phone number.

Electronic Wallet Ready to Pay Timer

Abstract: A mobile device having a time controlled electronic wallet is disclosed. The mobile device comprises a processor and an electronic wallet application that executes on the processor. The electronic wallet application enters a ready-to-pay mode, initiates a ready-to-pay timer when entering the ready-to-pay mode, transmits the confidential information when in the ready-to-pay mode based on receiving contactless communication, and leaves the ready-to-pay mode when the ready-to-pay timer expires.

Intelligent Automated Assistant

Abstract: An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Automated Response to and Sensing of User Activity in Portable Devices

Abstract: The various methods and devices described herein relate to devices which, in at least certain embodiments, may include one or more sensors for providing data relating to user activity and at least one processor for causing the device to respond based on the user activity which was determined, at least in part, through the sensors. The response by the device may include a change of state of the device, and the response may be automatically performed after the user activity is determined.

System and methods for recognizing sound and music signals in high noise and distortion

Abstract: A method for recognizing an audio sample locates an audio file that most closely matches the audio sample from a database indexing a large set of original recordings. Each indexed audio file is represented in the database index by a set of landmark timepoints and associated fingerprints. Landmarks occur at reproducible locations within the file, while fingerprints represent features of the signal at or near the landmark timepoints. To perform recognition, landmarks and fingerprints are computed for the unknown sample and used to retrieve matching fingerprints from the database. For each file containing matching fingerprints, the landmarks are compared with landmarks of the sample at which the same fingerprints were computed. If a large number of corresponding landmarks are linearly related, i.e., if equivalent fingerprints of the sample and retrieved file have the same time evolution, then the file is identified with the sample. The method can be used for any type of sound or music, and is particularly effective for audio signals subject to linear and nonlinear distortion such as background noise, compression artifacts, or transmission dropouts. The sample can be identified in a time proportional to the logarithm of the number of entries in the database; given sufficient computational power, recognition can be performed in nearly real time as the sound is being sampled.

Using context information to facilitate processing of commands in a virtual assistant

Abstract: A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Method and apparatus for building an intelligent automated assistant

Abstract: A method and apparatus are provided for building an intelligent automated assistant. Embodiments of the present invention rely on the concept of “active ontologies” (e.g., execution environments constructed in an ontology-like manner) to build and run applications for use by intelligent automated assistants. In one specific embodiment, a method for building an automated assistant includes interfacing a service-oriented architecture that includes a plurality of remote services to an active ontology, where the active ontology includes at least one active processing element that models a domain. At least one of the remote services is then registered for use in the domain.