Amazon Technologies, Inc.

Zhengping Jin

Sumit Garg

Ameya Agaskar

Christopher Evans

Mohammad Edris Qarghah

Ahmed Abdelal

Nagaraj Mahajan

David McGuire

Described herein is a system for performing watermark detection using multiple time shifts to increase a resolution of watermark detection. Instead of decoding blocks of successive audio frames (e.g., 10 ms of audio) using a single watermark decoder, watermark verification can be performed by decoding overlapping frame shifts using multiple decoders in parallel, thereby increasing a chance that one of the watermark decoders will be synchronized with the embedded audio watermark. For example, watermark verification may split audio data into parallel streams and decode using two decoders (e.g., 2× shifts-per-frame), four decoders (e.g., 4× shifts-per-frame), or the like. Increasing resolution by performing overlapping detection increases an accuracy of the watermark detection without changing the embedded audio watermark.

Decoding audio watermarks using time shifts

Described herein is a system for encoding audio watermarks with time extensions to enable enhanced watermark detection. An extended audio watermark may include an existing audio watermark and a watermark extension, enabling backwards compatibility with existing watermark detection while also enabling enhanced watermark detection with increased accuracy. For example, embedding the extended acoustic watermark enables (i) limited devices to perform watermark detection to detect the existing audio watermark, and (ii) improved devices to perform enhanced watermark detection to detect the extended audio watermark. As the extended audio watermark has a longer time duration than the existing audio watermark, an accuracy of performing enhanced watermark detection is increased relative to detecting the existing audio watermark alone.

Extended audio watermarks

Described herein is a system for encoding audio watermarks with frequency extensions to enable enhanced watermark detection. An extended audio watermark may include an existing audio watermark and a duplicate audio watermark, enabling backwards compatibility with existing watermark detection while also enabling enhanced watermark detection with increased accuracy. For example, embedding the extended audio watermark enables (i) limited devices to perform watermark detection to detect the existing audio watermark, and (ii) improved devices to perform enhanced watermark detection to detect the extended audio watermark. As the extended audio watermark includes redundancy in the form of duplicate audio watermark(s), an accuracy of performing enhanced watermark detection is increased relative to detecting the existing audio watermark alone.

Techniques for synthetic accuracy measurement of a content recognition system are described. According to some examples, a computer-implemented method includes generating, by a provider network, a reference fingerprint for a secondary content (e.g., advertisement) media file; generating, by the provider network, a synthetic fingerprint for a transformed version of the secondary content media file; inserting, by the provider network, the synthetic fingerprint into a stream of fingerprints of a plurality of media files; comparing, by a comparison service of the provider network, the stream of fingerprints including the synthetic fingerprint to the reference fingerprint to generate an indication of a match between the synthetic fingerprint and the reference fingerprint in the stream; and sending the indication of the match to a storage location.

Growing community of inventors

Waltham, MA, United States of America

Zhengping Jin