Amazon Technologies, Inc.

Patent Bots LLC

University of Michigan

Canyon IP Holdings, LLC

Jeffrey C O'Neill

Philip Ryan Hilmes

Amit Singh Chhetri

Bjorn Hoffmeister

Ramya Gopalan

Hugh Evan Secker-Walker

Ryan Paul Thomas

Jeffrey Penrod Adams

Stan Weidner Salvador

James David Meyers

Kenneth John Basye

William J Williams

Frederick Victor Weber

Thomas Schaaf

Jeffrey Paul Lilly

Robert M Nickel

Alfred O Hero, Iii

Eugene J Zalubas

Interactive natural language processing (NLP) results may be generated that allow a user to interact with the NLP results but do so in an offline manner so that the documents being processed need not be stored online. To provide interactive NLP results, event handlers may be attached to elements of the NLP results. A user may then select a word or phrase of the NLP results to cause computer software provided with the NLP to present the interactive features. For example, a user may click on a definite noun phrase to view information for diagnosing antecedent basis errors. For another example, a user may click on a word to view information about how that word is used in a document, such as viewing portions of the document that include the word or variants of the word.

Offline interactive natural language processing results

A wearable computer is configured to use beamforming techniques to isolate a user's speech from extraneous audio signals occurring within a physical environment. A microphone array of the wearable computer may generate audio signal data from an utterance from a user's mouth. A motion sensor(s) of the wearable computer may generate motion data from movement of the wearable computer. This motion data may be used to determine a direction vector pointing from the wearable computer to the user's mouth, and a beampattern may be defined that has a beampattern direction in substantial alignment with the determined direction vector to focus the microphone array on the user's mouth for speech isolation.

Beamforming for a wearable computer

Features are disclosed for managing the use of speech recognition models and data in automated speech recognition systems. Models and data may be retrieved asynchronously and used as they are received or after an utterance is initially processed with more general or different models. Once received, the models and statistics can be cached. Statistics needed to update models and data may also be retrieved asynchronously so that it may be used to update the models and data as it becomes available. The updated models and data may be immediately used to re-process an utterance, or saved for use in processing subsequently received utterances. User interactions with the automated speech recognition system may be tracked in order to predict when a user is likely to utilize the system. Models and data may be pre-cached based on such predictions.

Speech model retrieval in distributed speech recognition systems

A method and apparatus for synchronizing media content emitted from various sources is presented. Arrival timing of outputs from the various sources to a particular location is determined and adjusted to reduce synchronization delays at the particular location. Synchronization delays may be determined by detecting the media output from a combination of sources arriving at the location. Control messages are generated by processing the detected output and determining delays to be applied to corresponding sources.

Dynamic audio synchronization

Embodiments of systems and methods are described for inverting transformations of signals due to room acoustics. In some implementations, a transformation of a calibration signal from a particular location in a room may be determined. From this transformation, an inverse transformation may be determined and the inverse transformation may be applied to a speech signal received from a similar location.

Transformation inversion to reduce the effect of room acoustics

Beam forming for a wearable computer

An unsupervised acoustic modeling service for speech recognition is disclosed. A computing device may be present in a listening zone, such as a household or office, and may receive an audio signal that may include speech. In some instances, the speech is not directed to the computing device. Speech recognition results may be generated from the audio signal, using an acoustic model, and the results used to update the acoustic model. For example, the acoustic model may be updated to reflect a particular speaker's pronunciation of certain sound units, such as phonemes. By using speech that is not necessarily directed to the computing device, more data may be available for updating an acoustic model.

Unsupervised acoustic model training

Features are provided for selectively scoring portions of user utterances based at least on articulatory features of the portions. One or more articulatory features of a portion of a user utterance can be determined. Acoustic models or subsets of individual acoustic model components (e.g., Gaussians or Gaussian mixture models) can be selected based on the articulatory features of the portion. The portion can then be scored using a selected acoustic model or subset of acoustic model components. The process may be repeated for the multiple portions of the utterance, and speech recognition results can be generated from the scored portions.

Selective speech recognition scoring using articulatory features

A method for producing speech recognition results on a device includes receiving first speech recognition results, obtaining a language model, wherein the language model represents information stored on the device, and using the first speech recognition results and the language model to generate second speech recognition results.

Methods and systems for obtaining language models for transcribing communications

In a distributed automated speech recognition (ASR) system, speech models may be employed on a local device to allow the local device to process frequently spoken utterances while passing other utterances to a remote device for processing. Upon receiving an audio signal, the local device compares the audio signal to the speech models of the frequently spoken utterances to determine whether the audio signal matches one of the speech models. When the audio signal matches one of the speech models, the local device processes the utterance, for example by executing a command. When the audio signal does not match one of the speech models, the local device transmits the audio signal to a second device for ASR processing. This reduces latency and the amount of audio signals that are sent to the second device for ASR processing.

Local speech recognition of frequent utterances

A specific language model for speech recognition may be built. In some embodiments, the specific language model is associated with a user and built using a corpus of text obtained from a user computing device. In some embodiments, a sequence of words is constructed from the corpus of text. The sequence of words may be obfuscated, and the obfuscated sequence of words may be stored in the specific language model. A server or a user device may use the specific language model in conjunction with a general language model to perform speech recognition on an utterance made by the user.

Growing community of inventors

Somerville, MA, United States of America

Jeffrey C O'Neill