Abstract: A virtual assistant receives natural language interpretation hypotheses for user queries, determines entities and attributes from the interpretations, and requests data from appropriate data sources. A cost function estimates the cost of each data source request. Cost functions include factors such as contract pricing, access latency, and data quality. Based on the estimated cost, the virtual assistant sends requests to a plurality of data sources, each of which might be able to provide data necessary to answer the user query. By including user credits in the cost function, the virtual assistant provides better quality of results and answer latency for paying users. The virtual assistant minimizes latency by answering using data from the first responding data source or provides a latency guarantee by answering with the most accurate data received by a deadline. The virtual assistant measures data source response latency and caches responses for expensive requests.

Abstract: An ad processor evaluates bid functions that are based on concepts that might be generated from interpretations of natural language expressions. Ad buyers provide the functions with corresponding ads to ad processors. Bid functions are further based on the values of semantic information referenced by expressions. Bid functions are further based on environmental information. Ad buyers are able to modify bid functions. Ads may be provided in the form of questions, and may be indicated by an identifying sound. Upon finding no expression concepts within a bid function, the set of expression concepts is expanded according to strengths of connections between concepts in a concept graph.

Abstract: A foreign device (FD) authenticates a user by communicating with a personal device (PD) using an audible signal. A system detects audible signals within time windows, and the signals can include codes. Either of the FD and PD can emit an audible signal for reception by the other device. A system uses geolocation, and comparison of audio segments simultaneously captured by each device to determine proximity between the devices. Users can speak audible messages, such as a codes read from PD. Codes can be words or numbers. Either device can enable speech recognition for detecting codes. The FD can also capture a unique user ID. The system can use the unique user ID to lookup a PD's ID.

Abstract: A system and method is presented for performing dual mode speech recognition, employing a local recognition module on a mobile device and a remote recognition engine on a server device. The system accepts a spoken query from a user, and both the local recognition module and the remote recognition engine perform speech recognition operations on the query, returning a transcription and confidence score, subject to a latency cutoff time. If both sources successfully transcribe the query, then the system accepts the result having the higher confidence score. If only one source succeeds, then that result is accepted. In either case, if the remote recognition engine does succeed in transcribing the query, then a client vocabulary is updated if the remote system result includes information not present in the client vocabulary.

Abstract: A system and method is presented for performing dual mode speech recognition, employing a local recognition module on a mobile device and a remote recognition engine on a server device. The system accepts a spoken query from a user, and both the local recognition module and the remote recognition engine perform speech recognition operations on the query, returning a transcription and confidence score, subject to a latency cutoff time. If both sources successfully transcribe the query, then the system accepts the result having the higher confidence score. If only one source succeeds, then that result is accepted. In either case, if the remote recognition engine does succeed in transcribing the query, then a client vocabulary is updated if the remote system result includes information not present in the client vocabulary.

Abstract: The present disclosure relates to systems and methods that recognize audio queries and select related information to return in response to recognition of the audio queries. The technology disclosed facilitates easy designation of aggregate user experience categories and custom audio references to be recognized. It facilitates linking and returning of selected information in response to recognition of audio queries that match the designated aggregate user experience categories or custom audio references to be recognized.

Abstract: In one implementation, a method is described of retrying matching of an audio query against audio references. The method includes receiving a follow-up query that requests a retry at matching a previously submitted audio query. In some implementations, this follow-up query is received without any recognition hint that suggests how to retry matching. The follow-up query includes the audio query or a reference to the audio query to be used in the retry. The method further includes retrying matching the audio query using retry matching resources that include an expanded group of audio references, identifying at least one match and transmitting a report of the match. Optionally, the method includes storing data that correlates the follow-up query, the audio query or the reference to the audio query, and the match after retrying.

Abstract: A method for processing a voice message in a computerized system. The method receives and records a speech utterance including a message portion and a communication portion. The method proceeds to parse the input to identify and separate the message portion and the communication portion. It then identifies communication parameters, including one or more destination mailboxes, from the communication portion, and it transmits the message portion to the destination mailbox as a voice message.

Abstract: A method for matching a query against a broadcast stream includes receiving one or more broadcast streams, from which it generates and stores an audio fingerprint of a selected portion of each received broadcast stream. A query is received from which the method generates an audio fingerprint. From that point, the method continues by identifying audio content from the query, using the query audio fingerprint and a database of indexed audio content. The method concludes by identifying the source of the query using the query audio fingerprint and the stored audio fingerprints. Embodiments of the method further include predictively caching audio fingerprint sequences and corresponding audio item identifiers from a server after storing audio fingerprints extracted from the broadcast stream; and using the predictively cached audio fingerprint sequences to identify an audio item within the audio signal based on at least some additional audio fingerprints of the audio signal.

Abstract: A system and method are provided for adding user characterization information to a user profile by analyzing user's speech. User properties such as age, gender, accent, and English proficiency may be inferred by extracting and deriving features from user speech, without the user having to configure such information manually. A feature extraction module that receives audio signals as input extracts acoustic, phonetic, textual, linguistic, and semantic features. The module may be a system component independent of any particular vertical application or may be embedded in an application that accepts voice input and performs natural language understanding. A profile generation module receives the features extracted by the feature extraction module and uses classifiers to determine user property values based on the extracted and derived features and store these values in a user profile. The resulting profile variables may be globally available to other applications.

Abstract: A method for processing a natural language input to a computerized system. The method parses the input to identify a query portion and a communication portion of the input. The system then determines an answer to the query portion, including identifying communication parameters from the communication portion. Upon determining the answer, the system prepares an answer to the communication and transmits that answer. If the answer requires information from a remote source, the system creates a subsidiary query to obtain that information and then submits the subsidiary query to the remote source. A response to the query is used to compose the answer to the query from the answer to the subsidiary query. If the system concludes that the query portion does not require information from a remote source, analyzing and answering the query locally.

Abstract: A client, such as a mobile phone, receives an audio signal from a microphone; the sound comes from a broadcast signal such as a radio or television program. The client sends a segment of audio data from the broadcast program to a detection system, such as a server. A broadcast monitoring system receives many broadcast audio signals and encodes their fingerprints in a database for matching. The detection system compares the client's audio data fingerprints to the content fingerprints to identify which broadcast station broadcast the signal having the sampled content. This information enables the client to resume the experience of the broadcast from one of a number of possible media sources.

Abstract: The present invention relates to the continuous monitoring of an audio signal and identification of audio items within an audio signal. The technology disclosed utilizes predictive caching of fingerprints to improve efficiency. Fingerprints are cached for tracking an audio signal with known alignment and for watching an audio signal without known alignment, based on already identified fingerprints extracted from the audio signal. Software running on a smart phone or other battery-powered device cooperates with software running on an audio identification server.

Abstract: A system and method is presented for performing dual mode speech recognition, employing a local recognition module on a mobile device and a remote recognition engine on a server device. The system accepts a spoken query from a user, and both the local recognition module and the remote recognition engine perform speech recognition operations on the query, returning a transcription and confidence score, subject to a latency cutoff time. If both sources successfully transcribe the query, then the system accepts the result having the higher confidence score. If only one source succeeds, then that result is accepted. In either case, if the remote recognition engine does succeed in transcribing the query, then a client vocabulary is updated if the remote system result includes information not present in the client vocabulary.

Abstract: Systems and methods for searching cloud-based databases are provided herein. A service provider may have a need to make their database(s) searchable through search technology. However, the service provider may not have the resources to implement such search technology. The search technology may allow for search queries against these cloud-based databases. The technology described herein provides a solution addressing the service provider's need, by giving a search technology that furnishes search results in a fast, accurate manner. In further embodiments, systems and methods to monetize those search results are also described herein.

Abstract: The present invention relates to the continuous monitoring of an audio signal and identification of audio items within an audio signal. The technology disclosed utilizes predictive caching of fingerprints to improve efficiency. Fingerprints are cached for tracking an audio signal with known alignment and for watching an audio signal without known alignment, based on already identified fingerprints extracted from the audio signal. Software running on a smart phone or other battery-powered device cooperates with software running on an audio identification server.

Abstract: A method for processing a voice message in a computerized system. The method receives and records a speech utterance including a message portion and a communication portion. The method proceeds to parse the input to identify and separate the message portion and the communication portion. It then identifies communication parameters, including one or more destination mailboxes, from the communication portion, and it transmits the message portion to the destination mailbox as a voice message.

Abstract: Systems and methods for searching cloud-based databases are provided herein. A service provider may have a need to make their database(s) searchable through search technology. However, the service provider may not have the resources to implement such search technology. The search technology may allow for search queries against these cloud-based databases. The technology described herein provides a solution addressing the service provider's need, by giving a search technology that furnishes search results in a fast, accurate manner. In further embodiments, systems and methods to monetize those search results are also described herein.

Abstract: A system and method is presented for performing dual mode speech recognition, employing a local recognition module on a mobile device and a remote recognition engine on a server device. The system accepts a spoken query from a user, and both the local recognition module and the remote recognition engine perform speech recognition operations on the query, returning a transcription and confidence score, subject to a latency cutoff time. If both sources successfully transcribe the query, then the system accepts the result having the higher confidence score. If only one source succeeds, then that result is accepted. In either case, if the remote recognition engine does succeed in transcribing the query, then a client vocabulary is updated if the remote system result includes information not present in the client vocabulary.

Abstract: A method for processing a voice message in a computerized system. The method receives and records a speech utterance including a message portion and a communication portion. The method proceeds to parse the input to identify and separate the message portion and the communication portion. It then identifies communication parameters, including one or more destination mailboxes, from the communication portion, and it transmits the message portion to the destination mailbox as a voice message.