AT&T Intellectual Property I, LP

Nuance Communications, Inc.

Robert Bell

Kadangode K Ramakrishnan

Jeffrey Erman

Jeffrey Pang

Yifan Hu

Srinivas Bangalore

Mazin E Gilbert

Patrick Guy Haffner

Diamantino Antonio Caseiro

Yehuda Koren

Christopher Volinsky

Andrew G Gauld

Thomas Ostrand

Elaine Weyuker

A method that incorporates teachings of the subject disclosure may include, for example transmitting, via a connection to a network having an available digital bandwidth, a first pre-fetch media content item of media content items included in the a media recommendation transmitted to a communication device, the first pre-fetch media content item having a first rank. Responsive to a determination of a change in the available digital bandwidth, the transmitting of the first pre-fetch media content item is stopped and a second pre-fetch media content item of media content items included in the media recommendation is transmitted via the connection to the network. The second pre-fetch media content item has a second rank. Other embodiments are disclosed.

Method and apparatus for content distribution over a network

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating domain-specific speech recognition models for a domain of interest by combining and tuning existing speech recognition models when a speech recognizer does not have access to a speech recognition model for that domain of interest and when available domain-specific data is below a minimum desired threshold to create a new domain-specific speech recognition model. A system configured to practice the method identifies a speech recognition domain and combines a set of speech recognition models, each speech recognition model of the set of speech recognition models being from a respective speech recognition domain. The system receives an amount of data specific to the speech recognition domain, wherein the amount of data is less than a minimum threshold to create a new domain-specific model, and tunes the combined speech recognition model for the speech recognition domain based on the data.

System and method for rapid customization of speech recognition models

A method that incorporates teachings of the subject disclosure may include, for example performing, by a wireless communication device comprising a processor, wireless telephony communications via a first wireless interface, transmitting information associated with media-related activities to a server, receiving from the server a media recommendation that is generated according to the information associated with media-related activities, initiating communications with a network via a second wireless interface, downloading a media content item of the media recommendation from a content provider via the second wireless interface, and presenting the media content item at a display. Other embodiments are disclosed.

Disclosed herein are systems, methods and non-transitory computer-readable media for performing speech recognition across different applications or environments without model customization or prior knowledge of the domain of the received speech. The disclosure includes recognizing received speech with a collection of domain-specific speech recognizers, determining a speech recognition confidence for each of the speech recognition outputs, selecting speech recognition candidates based on a respective speech recognition confidence for each speech recognition output, and combining selected speech recognition candidates to generate text based on the combination.

System and method for combining speech recognition outputs from a plurality of domain-specific speech recognizers via machine learning

Systems and techniques for generating item ratings for a user in order to allow for recommendations of selected items for that user. A set of known ratings of different items for a plurality of users is collected and maintained, and these known ratings are used to estimate rating factors influencing ratings, including user and item factors. Initial user and item factors are estimated and new user and item factors are successively added, with the original rating factors being progressively shrunk so as to reduce their magnitude and their contribution to the rating estimation as successive factors are added. When an appropriate number of user and item factors has been estimated, the rating factors are used to estimate ratings of items for a user, and the estimated ratings are employed to generate recommendations for that user.

Methods and apparatus for modeling relationships at multiple scales in ratings estimation

A method, apparatus, and computer-readable medium for predicting the fault-proneness of code units (files, modules, packages, and the like) of large-scale, long-lived software systems. The method collects information about the code units and the development process from previous releases, and formats this information for input to an analysis stage. The tool then performs a statistical regression analysis on the collected data, and formulates a model to predict fault counts for code units of the current and future releases. Finally, the method computes an expected fault count for each code unit in the current release by applying the formulated model to data from the current release. The expected fault counts are used to rank the release units in descending order of fault-proneness so that debugging efforts and resources can be optimized.

Tool for predicting fault-prone software files

Systems and techniques for estimation of item ratings for a user. A set of item ratings by multiple users is maintained, and similarity measures for all items are precomputed, as well as values used to generate interpolation weights for ratings neighboring a rating of interest to be estimated. A predetermined number of neighbors are selected for an item whose rating is to be estimated, the neighbors being those with the highest similarity measures. Global effects are removed, and interpolation weights for the neighbors are computed simultaneously. The interpolation weights are used to estimate a rating for the item based on the neighboring ratings, Suitably, ratings are estimated for all items in a predetermined dataset that have not yet been rated by the user, and recommendations are made of the user by selecting a predetermined number of items in the dataset having the highest estimated ratings.

Growing community of inventors

Murray Hill, NJ, United States of America

Robert Bell