Abstract: Method and system to provide users with access to authoritative sets of various collectable items and to permit users create and manage their own sets based on the respective authoritative sets are described. An authoritative set may be a collection of images representing collectable items. Access to an authoritative set may be provided via a web site that facilitates a community space where users can compare their collected sets to the authoritative set and determine what products may be missing for their user's set.

Abstract: A system and method of metadata refinement using behavioral patterns is disclosed. In some embodiments, user behavioral data for results of a search query is received. The results can include an untagged item and a plurality of tagged items. A determination can then be made that the tagged items have been assigned a first type of metadata not assigned to the untagged item. The untagged item can then be identified as a candidate to be tagged with the first type of metadata assigned to the tagged items based on the user behavioral data. In some embodiments, the user behavioral data comprises clickstream data indicating that a user selected the untagged item and the tagged items during a single search event.

Abstract: Methods, computer-storage media, and graphical user interfaces are provided for identifying and presenting rich related sites for task-oriented search queries. Upon receipt of a search query input by a user, one or more query logs are analyzed to determine if the search query is a related to a task being performed by the user. If the query is determined to be a task-oriented search query, search results are identified, as is one or more Uniform Resource Locators (URLs) related to a particular search result. The related URL is presented to the user in association with the particular search result. Additional controls, e.g., search tools that facilitate querying of those URLs determined to be relevant to a particular search result, may also be provided to aid the user in performing the task at hand.

Abstract: Features are disclosed for automatically identifying a speaker. Artifacts of automatic speech recognition (“ASR”) and/or other automatically determined information may be processed against individual user profiles or models. Scores may be determined reflecting the likelihood that individual users made an utterance. The scores can be based on, e.g., individual components of Gaussian mixture models (“GMMs”) that score best for frames of audio data of an utterance. A user associated with the highest likelihood score for a particular utterance can be identified as the speaker of the utterance. Information regarding the identified user can be provided to components of a spoken language processing system, separate applications, etc.

Abstract: Methods and systems to build containers of uncategorized items are described. In some example embodiments, the methods and systems access a search query received by a network-based publication system, identify a container of uncategorized items having a title that satisfies the search query, and return a result for the search query that is associated with the identified container.

Abstract: Method and system to provide users with access to authoritative sets of various collectable items and to permit users create and manage their own sets based on the respective authoritative sets are described. An authoritative set may be a collection of images representing collectable items. Access to an authoritative set may be provided via a web site that facilitates a community space where users can compare their collected sets to the authoritative set and determine what products may be missing for their user's set.

Abstract: In an automatic speech recognition (ASR) processing system, ASR processing may be configured to reduce a latency of returning speech results to a user. The latency may be determined by comparing a time stamp of an utterance in process to a current time. Latency may also be estimated based on an endpoint of the utterance or other considerations such as how difficult the utterance may be to process. To improve latency the ASR system may be configured to adjust various processing parameters, such as graph pruning factors, path weights, ASR models, etc. Latency checks and corrections may occur dynamically for a particular utterance while it is being processed, thus allowing the ASR system to adjust to rapidly changing latency conditions.

Abstract: Systems and methods of providing composite search results are disclosed. A system may receive input via a user interface of a device accessing a first website, and determine item listing information of an item listed for sale on a second website based on the received input, with the second website being different from the first website. The system may cause the item listing information to be displayed on the first website on the device via the user interface, and enable the device to interact with the second website, via the user interface, regarding the item listed for sale by interacting with the item listing information being displayed on the first website.

Abstract: Determining the end of an utterance for purposes of automatic speech recognition (ASR) may be improved with a system that provides early results and/or incorporates semantic tagging. Early ASR results of an incoming utterance may be prepared based at least in part on an estimated endpoint and processed by a natural language understanding (NLU) process while final results, based at least in part on a final endpoint, are determined. If the early results match the final results, the early NLU results are already prepared for early execution. The endpoint may also be determined based at least in part on the content of the utterance, as represented by semantic tagging output from ASR processing. If the tagging indicate completion of a logical statement, an endpoint may be declared, or a threshold for silent frames prior to declaring an endpoint may be adjusted.

Abstract: Systems and methods of providing composite search results are disclosed. A search query may be received by a general purpose search engine of a first website from a user. At least one general purpose search result may be determined based on the search query using the general purpose search engine. The at least one general purpose search result may be based on a search of multiple websites. Item listing information of an item listed for sale on a second website may be determined based on the search query. The at least one general purpose search result and the item listing information may be caused to be displayed concurrently on the first website to the user. The user may be enabled to interact with the second website regarding the item by interacting with the item listing information displayed on the first website.

Abstract: Methods, computer-storage media, and graphical user interfaces are provided for identifying and presenting rich related sites for task-oriented search queries. Upon receipt of a search query input by a user, one or more query logs are analyzed to determine if the search query is a related to a task being performed by the user. If the query is determined to be a task-oriented search query, search results are identified, as is one or more Uniform Resource Locators (URLs) related to a particular search result. The related URL is presented to the user in association with the particular search result. Additional controls, e.g., search tools that facilitate querying of those URLs determined to be relevant to a particular search result, may also be provided to aid the user in performing the task at hand.

Abstract: Features are disclosed for managing the use of speech recognition models and data in automated speech recognition systems. Models and data may be retrieved asynchronously and used as they are received or after an utterance is initially processed with more general or different models. Once received, the models and statistics can be cached. Statistics needed to update models and data may also be retrieved asynchronously so that it may be used to update the models and data as it becomes available. The updated models and data may be immediately used to re-process an utterance, or saved for use in processing subsequently received utterances. User interactions with the automated speech recognition system may be tracked in order to predict when a user is likely to utilize the system. Models and data may be pre-cached based on such predictions.

Abstract: Methods, computer-storage media, and graphical user interfaces are provided for identifying and presenting rich related sites for task-oriented search queries. Upon receipt of a search query input by a user, one or more query logs are analyzed to determine if the search query is a related to a task being performed by the user. If the query is determined to be a task-oriented search query, search results are identified, as is one or more Uniform Resource Locators (URLs) related to a particular search result. The related URL is presented to the user in association with the particular search result. Additional controls, e.g., search tools that facilitate querying of those URLs determined to be relevant to a particular search result, may also be provided to aid the user in performing the task at hand.

Abstract: Features are disclosed for transferring speech recognition workloads between pooled execution resources. For example, various parts of an automatic speech recognition engine may be implemented by various pools of servers. Servers in a speech recognition pool may explore a plurality of paths in a graph to find the path that best matches an utterance. A set of active nodes comprising the last node explored in each path may be transferred between servers in the pool depending on resource availability at each server. A history of nodes or arcs traversed in each path may be maintained by a separate pool of history servers, and used to generate text corresponding to the path identified as the best match by the speech recognition servers.

Abstract: A layer system and a method for producing a component having such a layer system are provided. The layer system includes a substrate a substrate, at least one MCrX layer on the substrate, and a chromium-rich layer on or in the at least one MCrX layer. X includes at least one element selected from the group consisting of yttrium (Y), silicon (Si), aluminum (Al) and boron (B). M includes at least one element selected from the group consisting of nickel (Ni) and cobalt (Co).

Abstract: Features are disclosed for selecting and using multiple transforms associated with a particular remote device for use in automatic speech recognition (“ASR”). Each transform may be based on statistics that have been generated from processing utterances that share some characteristic (e.g., acoustic characteristics, time frame within which the utterances where processed, etc.). When an utterance is received from the remote device, a particular transform or set of transforms may be selected for use in speech processing based on data obtained from the remote device, speech processing of a portion of the utterance, speech processing of prior utterances, etc. The transform or transforms used in processing the utterances may then be updated based on the results of the speech processing.

Abstract: Features are disclosed for managing the use of speech recognition models and data in automated speech recognition systems. Models and data may be retrieved asynchronously and used as they are received or after an utterance is initially processed with more general or different models. Once received, the models and statistics can be cached. Statistics needed to update models and data may also be retrieved asynchronously so that it may be used to update the models and data as it becomes available. The updated models and data may be immediately used to re-process an utterance, or saved for use in processing subsequently received utterances. User interactions with the automated speech recognition system may be tracked in order to predict when a user is likely to utilize the system. Models and data may be pre-cached based on such predictions.

Abstract: A system and method of metadata refinement using behavioral patterns is disclosed. In some embodiments, user behavioral data for results of a search query is received. The results can include an untagged item and a plurality of tagged items. A determination can then be made that the tagged items have been assigned a first type of metadata not assigned to the untagged item. The untagged item can then be identified as a candidate to be tagged with the first type of metadata assigned to the tagged items based on the user behavioral data. In some embodiments, the user behavioral data comprises clickstream data indicating that a user selected the untagged item and the tagged items during a single search event.

Abstract: A user interface is provided which presents a text box representing an area in which a user can enter a proxy bid for an online auction, the text box being presented within a button operable by the user to activate the proxy bid. Then input is received from the user in the text box presented within the button. The input is then placed as a bid in the online auction upon receiving a selection of the button, the selection being indicated by an activation of the button outside the area represented by the text box.

Abstract: Systems and methods of providing composite search results are disclosed. A search query may be received by a general purpose search engine of a first website from a user. At least one general purpose search result may be determined based on the search query using the general purpose search engine. The at least one general purpose search result may be based on a search of multiple websites. Item listing information of an item listed for sale on a second website may be determined based on the search query. The at least one general purpose search result and the item listing information may be caused to be displayed concurrently on the first website to the user. The user may be enabled to interact with the second website regarding the item by interacting with the item listing information displayed on the first website.