Google Inc.

Boulos Harb

Arnaud Sahuguet

Alan C Strohm

Steven M Stern

Joseph Janos

Ademir De Alvarenga Oliveira

Jeffrey Adgate Dean

Sanjay Ghemawat

Ciprian Ioan Chelba

Michael Dennis Riley

Eugene Weinstein

Ademir De Alvarenga Oliveria

Anaya Misra

Pavel Golik

Alex Rudnick

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing entities using observations. In one aspect, a method includes receiving data identifying an entity; generating a user interface document that, when rendered by a user device, presents a plurality of attribute values to a user and allows the user to modify one or more of the plurality of attribute values; and storing an observation in a data store, the observation including a user-modified value of one of the plurality of attribute values and a context including one or more of the presented attribute values.

Managing information about entities using observations

Systems and methods for identifying music in a noisy environment are described. One of the methods includes receiving audio segment data. The audio segment data is generated from the portion that is captured in the noisy environment. The method further includes generating feature vectors from the audio segment data, identifying phonemes from the feature vectors, and comparing the identified phonemes with pre-assigned phoneme sequences. Each pre-assigned phoneme sequence identifies a known music piece. The method further includes determining an identity of the music based on the comparison.

Systems and methods for identifying music in a noisy environment

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to language models stored for digital language processing. In one aspect, a method includes the actions of generating a language model, including: receiving a collection of n-grams from a corpus, each n-gram of the collection having a corresponding first probability of occurring in the corpus, and generating a trie representing the collection of n-grams, the trie being represented using one or more arrays of integers, and compressing an array representation of the trie using block encoding; and using the language model to identify a second probability of a particular string of words occurring.

Back-off language model compression

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing entities using observations. In one aspect, a method includes receiving an observation, the observation including an updated piece of information about an entity and a context, wherein the context includes at least one value of an attribute describing the entity to which the updated piece of information relates; matching the received observation with a first cluster of observations representing the entity using the context; and associating the received observation with the first cluster of observations.

Managing information about entities using clusters of received observations

Managing information about entities using observations generated from user modified values

Growing community of inventors

New Haven, CT, United States of America

Boulos Harb