Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received and item-recognition techniques are performed to identify one or more items referenced in the content. An interactive element is generated that indicates information about a given referenced item, and that interactive element is displayed while the multimedia content is output. Selection of the interactive element may cause a purchasing user interface to be displayed with item and/or or payment information prepopulated based at least in part on identified attributes of the item and/or user preferences determined from historical purchase data associated with the user.

Abstract: Systems and methods for an intelligent inventory system are disclosed. The systems and methods described herein may receive data from a point-of-sale (POS) device of a merchant indicating an item to add to an inventory catalog of the merchant. A rate may be determined that is associated with how many times the item may be returned or exchanged with a similarly-situated merchant. Additionally, or alternatively, the rate may comprise a fluctuation in price for the item and/or an amount of times the item may be re-stocked and/or re-ordered by the similarly-situated merchant. If the determined rate exceeds a threshold rate, a suggestion may be sent to the POS device of the merchant. The suggestion may comprise a suggested second item rather than the item requested, a suggested price to charge for the item suggested, and/or a suggested quantity to order of the item requested.

Abstract: Techniques described herein are directed to interactive elements displayed in multimedia content. In an example, it is determined that multimedia content displays an item offered for sale by a merchant. Based on so determining, an interactive element is rendered that displays a representation of the item offered for sale by the merchant in place of a portion of the multimedia content. When an interaction by a user with the interactive element is detected, a graphical user interface is displayed that is configured to allow the user to purchase the item.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received that includes a representation of an item offered for sale by a merchant. A user profile of the viewer is determined. Identifying information including customized item details are generated based on the user profile. The identifying information is sent to a different application (on a same device or different device as the device that is playing the multimedia content), which allows for linkage of a merchant profile and user profile and enables payment for the item.

Abstract: Techniques described herein are directed to interactive elements displayed in multimedia content. In an example, it is determined that multimedia content displays an item offered for sale by a merchant. Based on so determining, an interactive element is rendered that displays a representation of the item offered for sale by the merchant in place of a portion of the multimedia content. When an interaction by a user with the interactive element is detected, a graphical user interface is displayed that is configured to allow the user to purchase the item.

Abstract: Techniques for identifying images that are representative of items of inventory are described herein. A service provider may receive a description of an item of inventory from a merchant. The service provider may search one or more databases for images representative of the item. The images may include a merchant-facing image used to represent the item on a user interface of a merchant computing device and a customer-facing image used to represent the item to a customer on a user interface of a merchant computing device and/or a customer computing device. The customer-facing image may include an image that is more detailed, accurate, and/or aesthetically pleasing than the merchant-facing image. The service provider may associate the merchant-facing and customer-facing images with the item and may cause the merchant-facing and the customer-facing images to render on displays of the merchant and customer computing devices to represent the item.

Abstract: Techniques described herein are directed to receiving audio input during playback of multimedia content to trigger purchase and payment for an item represented in the multimedia content. In an example, multimedia content is sent to a user device. The multimedia content may contain a representation of an item and an indication that the item can be purchased. Based on receipt of an indication that trigger words were spoken during playback, a recording is initiated. A purchase intent of the user for the item is determined based on the recording. A graphical user interface is displayed via the user device to initiate payment by the user for the item.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received that includes a representation of an item offered for sale by a merchant. A user profile of the viewer is determined. Identifying information including customized item details are generated based on the user profile. The identifying information is sent to a different application (on a same device or different device as the device that is playing the multimedia content), which allows for linkage of a merchant profile and user profile and enables payment for the item.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received and item-recognition techniques are performed to identify one or more items referenced in the content. An interactive element is generated that indicates information about a given referenced item, and that interactive element is displayed while the multimedia content is output. Selection of the interactive element may cause a purchasing user interface to be displayed with item and/or or payment information prepopulated based at least in part on identified attributes of the item and/or user preferences determined from historical purchase data associated with the user.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received and item-recognition techniques are performed to identify one or more items referenced in the content. An interactive element is generated that indicates information about a given referenced item, and that interactive element is displayed while the multimedia content is output. Selection of the interactive element may cause a purchasing user interface to be displayed with item and/or or payment information prepopulated based at least in part on identified attributes of the item and/or user preferences determined from historical purchase data associated with the user.

Abstract: Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received and item-recognition techniques are performed to identify one or more items referenced in the content. An interactive element is generated that indicates information about a given referenced item, and that interactive element is displayed while the multimedia content is output. Selection of the interactive element may cause a purchasing user interface to be displayed with item and/or or payment information prepopulated based at least in part on identified attributes of the item and/or user preferences determined from historical purchase data associated with the user.

Abstract: A transcription system automates the control of the playback of the audio to accommodate the user's ability to transcribe the words spoken. In some examples, a delay between playback and typed input is estimated by processing the typed words using a wordspotting approach. The estimated delay is used as in input to an automated speed control, for example, to maintain a target or maximum delay between playback and typed input.

Abstract: In a general aspect, an approach to query specification includes processing a query by identifying one or more terms and validating the terms using a first corpus of media elements. The result of the validation is used to form a modified query. In some examples, identifying the one or more terms is based on a second corpus of media elements, which may include a different type of media than the first corpus. In some examples, the validating of the terms includes accepting input from a user according to parts of the elements of the first corpus presented to the user.

Abstract: In an aspect, in general, method for aligning an audio recording and a transcript includes receiving a transcript including a plurality of terms, each term of the plurality of terms associated with a time location within a different version of the audio recording, forming a plurality of search terms from the terms of the transcript, determining possible time locations of the search terms in the audio recording, determining a correspondence between time locations within the different version of the audio recording associated with the search terms and the possible time locations of the search terms in the audio recording, and aligning the audio recording and the transcript including updating the time location associated with terms of the transcript based on the determined correspondence.

Abstract: In one aspect, a method for processing media includes accepting a query. One or more language patterns are identified that are similar to the query. A putative instance of the query is located in the media. The putative instance is associated with a corresponding location in the media. The media in a vicinity of the putative instance is compared to the identified language patterns and data characterizing the putative instance of the query is provided according to the comparing of the media to the language patterns, for example, as a score for the putative instance that is determined according to the comparing of the media to the language patterns.

Abstract: A method for speaker adaptation includes receiving a plurality of media files, each associated with a call center agent of a plurality of call center agents and receiving a plurality of terms. Speech processing is performed on at least some of the media files to identify putative instances of at least some of the plurality of terms. Each putative instance is associated with a hit quality that characterizes a quality of recognition of the corresponding term. One or more call center agents for performing speaker adaptation are determined, including identifying call center agents that are associated with at least one media file that includes one or more putative instances with a hit quality below a predetermined threshold. Speaker adaptation is performed for each identified call center agent based on the media files associated with the identified call center agent and the identified instances of the plurality of terms.

Abstract: An audio processing system makes use of a number of levels of compression or data reduction, thereby providing reduced storage requirements while maintaining a high accuracy of keyword detection in the original audio input.

Abstract: A method for determining a similarity between a first audio source and a second audio source includes: for the first audio source, determining a first frequency of occurrence for each of a plurality of phoneme sequences and determining a first weighted frequency for each of the plurality of phoneme sequences based on the first frequency of occurrence for the phoneme sequence; for the second audio source, determining a second frequency of occurrence for each of a plurality of phoneme sequences and determining a second weighted frequency for each of the plurality of phoneme sequences based on the second frequency of occurrence for the phoneme sequence; comparing the first weighted frequency for each phoneme sequence with the second weighted frequency for the corresponding phoneme sequence; and generating a similarity score representative of a similarity between the first audio source and the second audio source based on the results of the comparing.

Abstract: A method for speaker adaptation includes receiving a plurality of media files, each associated with a call center agent of a plurality of call center agents and receiving a plurality of terms. Speech processing is performed on at least some of the media files to identify putative instances of at least some of the plurality of terms. Each putative instance is associated with a hit quality that characterizes a quality of recognition of the corresponding term. One or more call center agents for performing speaker adaptation are determined, including identifying call center agents that are associated with at least one media file that includes one or more putative instances with a hit quality below a predetermined threshold. Speaker adaptation is performed for each identified call center agent based on the media files associated with the identified call center agent and the identified instances of the plurality of terms.

Abstract: A method includes accepting, via an input interface, a caller identifier parameter and a target value of at least one call series parameter; identifying, using a data processor, a plurality of calls each associated with the caller identifier parameter from amongst a set of calls stored in a call center database; analyzing, using the data processor, the identified plurality of calls to determine a value of the at least one call series parameter for the identified plurality of calls; comparing, using the data processor, the determined value of the at least one call series parameter with the target value of the at least one call series parameter; and defining, using the data processor, the identified plurality of calls as a call series based at least in part on results of the comparing.