Amazon Technologies, Inc.

Sonus Networks, Inc.

Ahmed Abdelal

Wassim Matragi

Nagaraj Mahajan

Sumit Garg

Sai Kiran Venkata Subramanya Rupanagudi

Shaun Jaikarran Bharrat

Oliver C Ibe

Aaron Challenner

Ameya Agaskar

Zhengping Jin

Vladimir Botchev

Pavas Kant

Siddharth Agrawal

Nathaniel White

Yuxuan Hao

Nui Chan

David McGuire

Rohinton Gonda

Terrence Yu

A system configured to perform content recognition using fingerprinting to recognize known media content. A device determines fingerprints based on decoded content data to be sent using a media interface component to an output component. Metadata related to the content/device/fingerprint may also be created. The fingerprints and metadata are sent by the device to a supporting system for orchestration and matching of the fingerprints to known media content.

Content recognition using fingerprinting

A system configured to perform content identification using fingerprinting to recognize known media content. The system may generate a reference database including reference fingerprints for each media content item to include in the content identification. In addition, the system may generate a hash table that associates individual frames of the reference fingerprints with identification information for corresponding media content items. When a device is playing media content, the system may perform content identification by generating query fingerprints representing the media content and comparing the query fingerprints to the reference database. For example, the system may match a query fingerprint to a reference fingerprint by identifying which of the reference fingerprints shares the most frames with the query fingerprint using the hash table. In addition, the system may use additional decision criteria to confirm a match, such as fine-grain matching or tracking successive fingerprints over time.

Content identification using fingerprinting

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.

Computer-implemented methods for synthetic accuracy measurement of a content recognition system

A non-intrusive objective speech quality assessment is performed on a degraded speech signal. The methods are well suited for systems where random and bursty packet losses may occur and/or packet stream regeneration may also occur prior to speech signal quality assessment. In one embodiment received packetized speech is analyzed to determine to an overall final signal quality score. A limited set of trained neural networks, e.g., 5, corresponding to different signal features, each determine a signal feature quality score. A trained joint quality score determination module determines a joint quality score based on the signal feature quality scores. Packet loss is estimated based on received packet header information and/or detected gap durations. The determined joint quality score is adjusted, based on estimated packet loss information obtained from examining the speech signal, network level statistics and/or codec parameters to generate the final quality score.

Methods and apparatus for signal quality analysis

Described are methods and apparatuses, including computer program products, for limiting server overload via client control. A first set of a plurality of requests are transmitted to a server at a first transmission rate during a first period of time. The first transmission rate is limited to be less than or equal to a first transmission limit rate. An overload value is determined based on whether at least two or more requests of the first set of requests for service satisfy an overload criterion. A second transmission limit rate is determined based on the overload value and the first transmission limit rate. A second set of a plurality of requests is transmitted to the server at a second transmission rate during a second period of time. The second transmission rate is limited to be less than or equal to the second transmission limit rate.

Adaptive rate control based on overload signals

Described are methods and apparatuses, including computer program products, for controlling server resources. An occupancy value of a buffer and a first utilization value of a first processor are measured. The buffer is configured to store one or more requests for service from at least a first client. The first processor is configured to receive and process the one or more requests from the buffer. A buffer size value is determined based on a processor throughput calculation, and a first service request limit for the first client is determined based on the occupancy value, the first utilization value, and the buffer size value.

Hybrid server overload control scheme for maximizing server throughput

Growing community of inventors

North Andover, MA, United States of America

Ahmed Abdelal