Abstract: Systems and methods are described for generating speech signals using an encoder/decoder that synthesizes human voice signals (a “vocoder”). A processor may receive inputs that include a plurality of mel scale spectrograms, a fundamental frequency signal, and a constant noise signal. The received inputs may be encoded into two vector sequences by concatenating the received inputs and then filtering a result of the concatenating operation. A plurality of harmonic samples may be generated from one of the two generated vector sequences using an additive oscillator. The harmonic samples may be generated using processing steps that include applying a sigmoid non-linearity to the one of the two generated vector sequences. Each of the plurality of harmonic samples may then be used to create a vector, which may be used as an input for a convolutional decoder for adversarial training. The convolutional decoder may output the speech signals based on the vector made up of the plurality of harmonic samples.

Abstract: Example embodiments provide a system and method for inferring preferences from message metadata and conversations. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including inferring a preference of a user among the one or more users based on metadata in the communication. The networked system triggers a search process based in part on the inferred preference. The networked system then generates and transmits to the user a customized response comprising results of the search process.

Abstract: Example embodiments provide a system and method for inferring preferences from message metadata and conversations. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including inferring a preference of a user among the one or more users based on metadata in the communication. The networked system triggers a search process based in part on the inferred preference. The networked system then generates and transmits to the user a customized response comprising results of the search process.

Abstract: Example embodiments provide a system and method for inferring preferences from message metadata and conversations. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including inferring a preference of a user among the one or more users based on metadata in the communication. The networked system triggers a search process based in part on the inferred preference. The networked system then generates and transmits to the user a customized response comprising results of the search process.

Abstract: A machine is configured to access a search phrase or other communicated phrase and deconstruct the accessed phrase into multiple sub-phrases. The machine performs an analysis of n-grams that occur within the sub-phrases, generates a set of potentially different sub-phrases from the n-grams, and selects which data source among multiple available video sources should be accessed for each generated sub-phrase in the generated set. For example, the machine may allocate each generated sub-phrase to a corresponding data source and cause the corresponding data source to execute a query based on its corresponding sub-phrase. Thus, the machine chooses from which data source to obtain partial search results that correspond to each sub-phrase generated based on the analyzed n-grams in the accessed phrase.

Abstract: Example embodiments provide a system and method for analyzing conversations and determining whether to participate with a response. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including parsing key terms from the communication. The networked system then identifies a sentiment of a user among the one or more users based on the parsed key terms. Based on the identified sentiment, the networked system determines whether to respond to the communication. In response to a determination to respond, the networked system generates a customized response and transmits the customized response, over the network, to a device of the user. The customized response may comprise questions or a set of options related to the conversation.

Abstract: A machine is configured to perform an example method that causes the machine to parse sub-phrases within a phrase, recognize that a sub-phrase has or can have a geographically specific meaning, and notify a user that the sub-phrase is being processed using the geographically specific meaning. For example, supposing a user has communicated a phrase, the machine builds sub-phrases from the n-grams of the phrase and detects that an n-gram has a geographically specific meaning, thus disambiguating the n-gram. This disambiguation is performed using one or more geographically specific databases of n-grams. The machine determines that a geographical location is relevant to the n-gram, selects a specialized search procedure for the n-gram, and obtains search results using the selected specialized search procedure. The machine may also notify the user that the n-gram or a sub-phrase in which the n-gram appears is being processed using the geographically specific meaning.

Abstract: Example embodiments provide a system and method for analyzing conversations and determining whether to participate with a response. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including parsing key terms from the communication. The networked system then identifies a sentiment of a user among the one or more users based on the parsed key terms. Based on the identified sentiment, the networked system determines whether to respond to the communication. In response to a determination to respond, the networked system generates a customized response and transmits the customized response, over the network, to a device of the user. The customized response may comprise questions or a set of options related to the conversation.

Abstract: Example embodiments provide a system and method for analyzing conversations and determining whether to participate with a response. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including parsing key terms from the communication. The networked system then identifies a sentiment of a user among the one or more users based on the parsed key terms. Based on the identified sentiment, the networked system determines whether to respond to the communication. In response to a determination to respond, the networked system generates a customized response and transmits the customized response, over the network, to a device of the user. The customized response may comprise questions or a set of options related to the conversation.

Abstract: A machine is configured to perform an example method that causes the machine to parse sub-phrases within a phrase, recognize that a sub-phrase has or can have a geographically specific meaning, and notify a user that the sub-phrase is being processed using the geographically specific meaning. For example, supposing a user has communicated a phrase, the machine builds sub-phrases from the n-grams of the phrase and detects that an n-gram has a geographically specific meaning, thus disambiguating the n-gram. This disambiguation is performed using one or more geographically specific databases of n-grams. The machine determines that a geographical location is relevant to the n-gram, selects a specialized search procedure for the n-gram, and obtains search results using the selected specialized search procedure. The machine may also notify the user that the n-gram or a sub-phrase in which the n-gram appears is being processed using the geographically specific meaning.

Abstract: A machine is configured to access a search phrase or other communicated phrase and deconstruct the accessed phrase into multiple sub-phrases. The machine performs an analysis of n-grams that occur within the sub-phrases, generates a set of potentially different sub-phrases from the n-grams, and selects which data source among multiple available video sources should be accessed for each generated sub-phrase in the generated set. For example, the machine may allocate each generated sub-phrase to a corresponding data source and cause the corresponding data source to execute a query based on its corresponding sub-phrase. Thus, the machine chooses from which data source to obtain partial search results that correspond to each sub-phrase generated based on the analyzed n-grams in the accessed phrase.

Abstract: Example embodiments provide a system and method for inferring preferences from message metadata and conversations. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including inferring a preference of a user among the one or more users based on metadata in the communication. The networked system triggers a search process based in part on the inferred preference. The networked system then generates and transmits to the user a customized response comprising results of the search process.

Abstract: Example embodiments provide a system and method for automatically initiating actions on behalf of a user. A networked system generates a search query associated with a travel itinerary of a user and causes a search to be performed using the search query, The networked system detects a condition associated with the travel itinerary that triggers automatically holding a travel component on behalf of the user. In response to detecting the condition, the networked system automatically triggers placement of a hold on the travel component. The networked system then generates and transmits, over a network, a notification to a device of the user indicating the automatically held travel component.

Abstract: Example embodiments provide a system and method for analyzing conversations and determining whether to participate with a response. A networked system receives, over a network, a communication that is a part of a conversation involving one or more users, whereby the networked system is a participant in the conversation. The networked system analyzes the communication including parsing key terms from the communication. The networked system then identifies a sentiment of a user among the one or more users based on the parsed key terms. Based on the identified sentiment, the networked system determines whether to respond to the communication. In response to a determination to respond, the networked system generates a customized response and transmits the customized response, over the network, to a device of the user. The customized response may comprise questions or a set of options related to the conversation.