Microsoft Technology Licensing, LLC

Nuance Communications, Inc.

Linkedin Corporation

Yahoo! Inc.

Ashvin Kannan

Hy Murveit

Nihar Niranjan Mehta

Sanjay Sureshchandra Dubey

Sanjay Kshetramade

Ben Shahshahani

Carleton Miyamoto

Chris Leggetter

Katherine Knill

Deepak Agarwal

Lihong Pei

Guangyu Dong

Kai Wei

Jan O Pedersen

Chad Carson

Rukmini Iyer

Erick Cantu-Paz

Pero Subasic

Huining Feng

Christopher C LuVogt

Michael Grishaver

Christopher John Leggetter

David Cho-Lun Ku

Christopher J Leggetter

Gyanda Sachdeva

Michael Schuster

A system and method may optional include or utilize a processor configured to receive a request for social network content for display in a sponsored content position in a newsfeed of a social network interface, the position having a position criterion, identify a sponsored content item of multiple sponsored content items stored on a database based, at least in part, on a characteristic of the sponsored content item meeting the position criterion, a bid associated with the sponsored content item, and a scaling factor, wherein each of the sponsored content items correspond to one of multiple item types and at least two of the sponsored content items are of a different item type. The scaling factor for each of the sponsored content items is based on the item type of the corresponding one of the sponsored content items.

System and method for positioning sponsored content in a social network interface

Techniques for facilitating retargeting of content are described. According to various embodiments, a user specification of a first set of content items and a second set of content items may be received. Moreover, a user specification of flow logic information may be received. The flow logic information may specify a user trigger action, and an instruction that a second content item in the second set is only to be displayed to a particular user after it is determined that the particular user has performed the user trigger action on the first content item. Thereafter, it may be determined that the particular user has performed the user trigger action on the first content item, and the second content item may be displayed to the particular user, based on the flow logic information.

Techniques for facilitating content retargeting

A system and method optionally includes or utilizes a processor may receive a request for social network content for display in a position of a plurality of sponsored content positions in a newsfeed of a social network interface, each of the plurality of sponsored content positions having a position criterion, at least two of the plurality of sponsored content positions having a different position criterion and identify a sponsored content item of a plurality of sponsored content items stored on a database based, at least in part, on a characteristic of the sponsored content item meeting the position criterion and a bid associated with the sponsored content item. A transmitter may transmit the sponsored content item from the processor to a server for display on a user interface.

A system may include a database configured with individual partitions, one of the partitions corresponding to a sponsored content campaign of a social network. The system may further include multiple servers each communicatively coupled to the database, and each configured to implement a campaign having a campaign termination criterion. Each of the servers may include a processor configured to track sponsored content event data received from a user device based on the campaign and transmit the event data to the database and terminate the campaign based on a comparison of the event data as received from a partition of the database corresponding to the campaign and an estimation of event data not received from the database. The database may be configured to store the event data as received from the servers in the partition corresponding to the campaign upon receipt of the event data.

Independent targeted sponsored content management system and method

A machine may be configured to generate and provide, for example, a voice-user interface to a social networking service. The voice-user interface may enable a member of the social networking service to access member profile information for other members of the social networking service. Using the voice-user interface, a first member of the social networking service can speak a natural language command or request to receive an aural response that includes information regarding a second member of the social networking service. In this manner, the first member can request and receive specific member profile information of a second member. In another aspect, the first member can record audio notes to be assigned to his or her own member profile or assigned to a member profile of the second member. The first member may subsequently use the voice-user interface to have such audio notes played back when desired.

Voice interface to a social networking service

The present invention is directed towards systems and methods for predicting a frequency with which an advertisement displayed in response to a query will be selected. The method of the present invention comprises receiving analytics data associated with a display of one or more advertisements in response to one or more queries. One or more features associated with the one or more advertisements displayed in response to the one or more queries are identified. One or more functions are generated for predicting a frequency with which a given advertisement displayed in response to a query will be selected using the analytics data and features associated with the one or more advertisements displayed in response to the one or more queries.

System and method for generating functions to predict the clickability of advertisements

Method and apparatus for multi-pass speech recognition. An input device receives spoken input. A processor performs a first pass speech recognition technique on the spoken input and forms first pass results. The first pass results include a number of alternative speech expressions, each having an assigned score related to the certainty that the corresponding expression correctly matches the spoken input. The processor selectively performs a second pass speech recognition technique on the spoken input according to the first pass results. Preferably, the second pass attempts to correctly match the spoken input to only those expressions which were identified during the first pass. Otherwise, if one of the expressions identified by the first pass is assigned a score higher than a predetermined threshold (e.g., 95%), the second pass is not performed. Because the second pass is performed only when necessary, the invention recognizes speech with a faster average speed for a given accuracy in comparison to prior systems.

Selective multi-pass speech recognition system and method

Method and apparatus for multi-pass speech recognition. An input device receives spoken input. A processor performs a first pass speech recognition technique on the spoken input and forms first pass results. The first pass results include a number of alternative speech expressions, each having an assigned score related to the certainty that the corresponding expression correctly matches the spoken input. The processor selectively performs a second pass speech recognition technique on the spoken input according to the first pass results. Preferably, the second pass attempts to correctly match the spoken input to only those expressions which were identified during the first pass. Otherwise, if one of the expressions identified by the first pass is assigned a score higher than a predetermined threshold (e.g., 95%), the second pass is not performed. Because the second pass is performed only when necessary, the invention recognizes speech with a faster average speed for a given accuracy in comparison to prior systems. Alternately, the first pass results identify a characteristic of the spoken input. The characteristic can be the gender of the speaker or a type of telephone the speaker is calling from. In which case, the second pass speech recognition technique is selected from a plurality of speech recognition techniques according to the characteristic identified by the first pass. Because the selected second pass technique is specific to the characteristic of the spoken input, the second pass technique can perform speech recognition faster for a given accuracy than a technique which is not specific.

Adaptive multi-pass speech recognition system

Speech recognition system to selectively utilize different speech recognition techniques over multiple speech recognition passes

A technique for adaptation of a speech recognizing system across multiple remote communication sessions with a speaker. The speaker can be a telephone caller. An acoustic model is utilized for recognizing the speaker's speech. Upon initiation of a first remote session with the speaker, the acoustic model is speaker-independent. During the first session, the speaker is uniquely identified and speech samples are obtained from the speaker. In the preferred embodiment, the samples are obtained without requiring the speaker to engage in a training session. The acoustic model is then modified based upon the samples thereby forming a modified model. The model can be modified during the session or after the session is terminated. Upon termination of the session, the modified model is then stored in association with an identification of the speaker. During a subsequent remote session, the speaker is identified and, then, the modified acoustic model is utilized to recognize the speaker's speech. Additional speech samples are obtained during the subsequent session and, then, utilized to further modify the acoustic model. In this manner, an acoustic model utilized for recognizing the speech of a particular speaker is cumulatively modified according to speech samples obtained during multiple sessions with the speaker. As a result, the accuracy of the speech recognizing system improves for the speaker even when the speaker only engages in relatively short remote sessions.

Adaptation of a speech recognition system across multiple remote sessions with a speaker

The present invention introduces a system and method for dynamically improving speech recognition in a speech recognition or other speech processing system. The method comprises dynamically adjusting the system, which comprises estimating the utilization of resources in the system; and improving the performance of the system according to the availability of resources.

Method and system for dynamically improving performance of speech recognition or other speech processing systems

Growing community of inventors

Sunnyvale, CA, United States of America

Ashvin Kannan