Real-time audio recognition using multiple recognizers

摘要

An audio recognition service recognizes an audio sample across multiple content types. At least a partial set of results generated by the service are returned to a client while the audio sample is still being recorded and/or transmitted. The client additionally displays the results in real-time or near real-time to the user. The audio sample can be sent over a first HTTP connection and the results can be returned over a second HTTP connection. The audio recognition service further processes check-in selections received from the client for content items indicated by the results. Responsive to receiving the check-in selections, the service determines whether a user is eligible for a reward. If the user is eligible, the service provides the reward.

主权项

1. A method, comprising:
receiving, by a system including a processor from a client device over a first communication connection, a transmission of an audio recording made by the client device; while receiving the transmission, concurrently sending, by the system, a representation of an audio sample derived from the audio recording to a plurality of recognition modules, wherein respective recognition modules are configured to recognize distinct types of content; receiving, by the system prior to receiving all of the audio recording, from the plurality of recognition modules, a set of results identifying content items matching the representation of the audio sample; and transmitting, by the system to the client device over a second communication connection that is different from the first communication connection and prior to receiving all of the audio recording, the set of results.