Soundhound, Inc.

Fluential, LLC

Nant Holdingsip, LLC

Jun Huang

Bernard Mont-Reynaud

Kiran Garaga Lokeswarappa

Joel Gedalius

Farzad Ehsani

Demitrios Leo Master

Yookyung Kim

Keyvan Mohajer

Aaron Master

Timothy P Stonehocker

Youssef Billawala

Benjamin John Levitt

A computer-implemented method is provided. The method including receiving speech audio of dictation associated with a user ID, deriving acoustic features from the speech audio, storing the derived acoustic features in a user profile associated with the user ID, receiving a request for acoustic features through an application programming interface (API), the request including the user ID, and sending the derived acoustic features through the API.

Deriving acoustic features and linguistic features from received speech audio

A method is provided for advertisement selection. The method includes recognizing words from user speech over a large number of interactions, computing a number of unique words uttered during the interactions, classifying the user by the number of unique words uttered during the interactions, and selecting an advertisement targeted to the classified users.

Advertisement selection by linguistic classification

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.

Method and system for building an integrated user profile

The performance of traditional speech recognition systems (as applied to information extraction or translation) decreases significantly with, larger domain size, scarce training data as well as under noisy environmental conditions. This invention mitigates these problems through the introduction of a novel predictive feature extraction method which combines linguistic and statistical information for representation of information embedded in a noisy source language. The predictive features are combined with text classifiers to map the noisy text to one of the semantically or functionally similar groups. The features used by the classifier can be syntactic, semantic, and statistical.

Robust information extraction from utterances

Systems and methods for recognizing sounds are provided herein. User input relating to one or more sounds is received from a computing device. Instructions, which are stored in memory, are executed by a processor to discriminate the one or more sounds, extract music features from the one or more sounds, analyze the music features using one or more databases, and obtain information regarding the music features based on the analysis. Further, information regarding the music features of the one or more sounds may be transmitted to display on the computing device.

Systems and methods for sound recognition

Systems and methods for recognizing sounds are provided herein. User input relating to a sound is received from a computing device. Instructions, which are stored in memory, are executed by a processor to discriminate the sound, analyze one or more databases using data included in the discriminated sound, the one or more databases being selected based upon the discrimination of the sound. Additionally, the processor may be executed to obtain information regarding the discriminated sound, from the one or more databases, based on the analysis, and in response to the search query, transmitting for display the information regarding the discriminated sound to the computing device.

The present invention adopts the fundamental architecture of a statistical machine translation system which utilizes statistical models learned from the training data and does not require expert knowledge for rule-based machine translation systems. Out of the training parallel data, a certain amount of sentence pairs are selected for manual alignment. These sentences are aligned at the phrase level instead of at the word level. Depending on the size of the training data, the optimal amount for manual alignment may vary. The alignment is done using an alignment tool with a graphical user interface which is convenient and intuitive to the users. Manually aligned data are then utilized to improve the automatic word alignment component. Model combination methods are also introduced to improve the accuracy and the coverage of statistical models for the task of statistical machine translation.

Growing community of inventors

Fremont, CA, United States of America

Jun Huang