International Business Machines Corporation

Nuance Communications, Inc.

Martin Franz

Vittorio R Castelli

Jeffrey Scott McCarley

Sarbajit Kumar Rakshit

Radu Florian

Robert T Ward

Salim E Roukos

Ruchi Mahindru

Xin Zhou

Mark Edward Epstein

Girija Yegnanarayanan

Jeffrey Scott Sorensen

Avirup Sil

Salim Estephan Roukos

Peder Andreas Olsen

Kenneth W Church

Jason William Pelecanos

Taesun Moon

Sinem Guven Kaya

Stephen A Della Pietra

Miroslav Novak

Gourab Kundu

Nicholas Stephen Kersting

John Ferdinand Pitrelli

Imed Zitouni

Brian William Delaney

Neal Snider

Weizhong Zhu

Robert E Donovan

Scott McCarley

Vitorrio Castelli

Joshua David Koppelman

A method for estimating response relevance with respect to a received query includes receiving a set of user feedback items, a set of historical feedback data, and a set of context data, creating a user profile model according to the set of historical feedback data, wherein the user profile model indicates a weighting attribute based on the set of historical feedback data, weighting the set of user feedback items according to the created user profile model, creating a response relevance estimation model based on the weighted set of user feedback items, the received set of context data, and the received set of historical feedback data, and ranking one or more responses according to the created response relevance estimation model. The method may further include adjusting the user profile model and the response relevance estimation model responsive to receiving additional data.

Query response relevance determination

In an approach to synchronize notifications created in a VR environment to be presented in a physical environment at another time, notifications may be mapped across all relevant environments and associated with conditions that, when triggered, cause a notification to be presented to the user. Computer-implemented methods may include receiving natural language requests at a computing device in a first environment at a first time; parsing the natural language request into semantic components comprising an alert component and a content component; determining one or more conditions based on the alert component and the content component; mapping the semantic components to the plurality of environments; and executing a notification by the computing device, the notification representing the alert component and the content component in a second environment of the plurality of environments if the one or more conditions is satisfied at a second time that is later than the first time.

Synchronizing virtual reality notifications

Described are techniques for video conversion for accessibility including a technique comprising determining, using data from at least one camera, that a user is distracted based on a direction of gaze of the user with respect to a display device presenting video content. The technique further comprises converting, by a machine learning model, the video content to audio content in response to determining the user is distracted, wherein the audio content comprises a description of the video content. The technique further comprises outputting, using at least one speaker, the audio content to the user while the user is distracted.

Video content conversion

A roadway condition predictive model that can recommend ameliorative roadway action(s) is disclosed. A roadway controller computer acquires sensor and location information, which describe physical driving surface conditions on the roadway, from a plurality of vehicles that travel on the roadway. The roadway controller computer also acquires environmental and traffic conditions for the roadway. The roadway controller computer creates a predictive model that describes a deterioration rate and future physical condition of the roadway, based on the acquired sensor, location information, environmental and traffic conditions for the roadway. The roadway controller computer then implements an action to ameliorate deterioration of the roadway that is predicted by the predictive model.

Roadway condition predictive models

A method and system to monitor electrical devices. A failed first component electric demand profile based on a set of observed measured electric power consumption datasets associated with a failure of a first component of an electrical device is received. At least one characteristic specification of electric power consumption for the electrical device is determined. The electrical device includes a number of components. An operational measurement corresponding to a corresponding characteristic specification within the at least one characteristic specification for the electrical device over a time duration is received. The operational measurement is compared to the corresponding characteristic specification for the electrical device, the comparing including determining an operational condition indicating an upcoming failure of the first component. Based on the comparing, an operational condition from within a plurality of operating conditions of the electrical device is identified and indicated.

Device operations monitoring

A method, system, and/or computer program product mitigate vibration caused by sympathetic resonance in a structure that is physically proximate to a machine. One or more processors, based on readings from a resonance sensor, detect vibration caused by sympathetic resonance in a structure that is physically proximate to the machine. One or more processors then direct a machine component controller to adjust the machine component in order to mitigate the vibration.

Reducing noise generated by a motorized device

Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.

Methods and apparatus for extracting facts from a medical text

Embodiments of the present invention provide a computer-implemented method for communicating a reference code for a transaction. The method monitors a communication session conducted between a user and an agent via a communication channel, extracts user and channel properties from the monitored communication session, selects a reference code from a set of references codes stored on a database, in which the selection is based at least in part on the extracted communication channel properties and the extracted user properties, and then communicates the selected reference code to the user.

Adaptive selection of message data properties for improving communication throughput and reliability

A method and system to monitor electrical devices. At least one characteristic electric power consumption profile is determined for an operational cycle for an electrical device. The electrical device includes a number of components that each operate at respective time intervals within the operational cycle. A measured electric power consumption dataset is received, from an electrical power measurement apparatus connected to a power input of the electrical device, for the electrical device where the measured electric power consumption dataset includes measurements of electrical consumption by the electrical device over a time duration corresponding to at least part of the operational cycle. The measured electric power consumption dataset is compared to the at least one characteristic electrical power consumption profile associated with the electrical device. Based on the comparing, an operational condition from within a plurality of operating conditions of the electrical device is indicated.

A method, system, and/or computer program product mitigate sympathetic resonance in a structure that is physically proximate to a machine. One or more processors, based on readings from a sound sensor associated with a machine, detect a sound generated by a machine component of the machine. One or more processors, based on readings from a resonance sensor, detect vibration caused by sympathetic resonance in a structure that is physically proximate to the machine, where the sympathetic resonance is caused by the sound generated by the machine component. One or more processors then direct a machine component controller to adjust the machine component in order to mitigate the sympathetic resonance in the structure that is physically proximate to the machine.

An improved method, apparatus, and computer instructions displaying search results. A query is received in a first language. A snippet in the document containing the word is selected in response to identifying a document in a second language in which the document contains a word matching a query word in the query. This snippet is translated into the first language.

Display of results of cross language search

In an Automatic Speech Recognition (ASR) system having at least two language models, a method is provided for combining language model scores generated by at least two language models. A list of most likely words is generated for a current word in a word sequence uttered by a speaker, and acoustic scores corresponding to the most likely words are also generated. Language model scores are computed for each of the most likely words in the list, for each of the at least two language models. A set of coefficients to be used to combine the language model scores of each of the most likely words in the list is respectively and dynamically determined, based on a context of the current word. The language model scores of each of the most likely words in the list are respectively combined to obtain a composite score for each of the most likely words in the list, using the set of coefficients determined therefor.

Dynamic language model mixtures with history-based buckets

There is provided a method for compressing an index file in an information retrieval system that retrieves information from a plurality of documents. Each of the plurality of documents has features occurring therein. Each of the features has parameters corresponding thereto. Parameter values corresponding to the parameters of the features are mapped into a plurality of bins. Bin identifiers are stored in the index file. Each of the bin identifiers identifies a bin to which is assigned at least one individual parameter value corresponding to at least one individual parameter.

Compressing index files in information retrieval

An audio indexing system including, in addition to a speech recognition subsystem for converting the audio information into a textual form and an indexing subsystem for extracting the features to be used for searching and browsing, a statistical machine translation model, trained on a parallel or comparable corpus of automatically and by-hand transcribed data, for processing the output of the speech recognition system.

Indexing with translation model for feature regularization

A method of indexing a database of documents, by providing a vocabulary of n terms, indexing the database in the form of a non-negative n&#xd7;m index matrix V, wherein each of its m columns represents an jdocument having n entries containing a function of the number of occurrences of a iterm of said vocabulary appearing in said jdocument, factoring out non-negative matrix factors T and D such that V&#x2248;TD, and wherein T is an n&#xd7;r term matrix, D is an r&#xd7;m document matrix, and r&#x3c;nm/(n+m). The index so generated is useful in two-pass information retrieval systems.

Growing community of inventors

Yorktown Heights, NY, United States of America

Martin Franz