Nuance Communications, Inc.

Microsoft Technology Licensing, LLC

Dragon Systems, Inc.

Voice Signal Technologies, Inc.

Semantic Machines, Inc.

Scansoft, Inc.

Cerence Operating Company

Michael Jack Newman

Laurence Steven Gillick

Michael D Edgington

David Mark Krowitz

Anthony Gillet

Daniel Lawrence Roth

David Leo Wright Hall

Robert S Roth

Paul Adrian Van Mulbregt

Steven Andrew Wegmann

Joel M Gould

Nigel Robin Ellis

Anil Kumar Nori

Daniel Louis Klein

Jesse Daniel Eskes Rusak

Gregory Scott Friedman

Jordan Rian Cohen

Bekim Demiroski

Adam David Pauls

Dhananjay Bansal

Andrew Volpe

Jacob Daniel Andreas

Allan Gold

Pengyu Chen

Charles E Ingold

Jonathan P Yamron

Steven A Wegmann

Daniell Stevens

David Abrahams

Dean Sturtevant

Thomas E Lynch

Taylor Darwin Berg-Kirkpatrick

Michael Pizzo

Mark Fanty

Jason Todd Hunter

Michael Eric Deem

Srinivasmurthy P Acharya

Timothy Lynch

Michael B Taylor

Jeffrey T Pearce

Amit Shukla

Barbara R Peskin

Jason Michael Eisner

Samuel McIntire Thomson

Emmanouil Antonios Platanios

Jean Crawford

Charles Clayton Wooters

Venkatesh Nagesha

Andres Corrada-Emmanuel

Sanjay Nagamangalam

Yoshiko Ito

William D Alexander

Jiawei Zhou

Robert Roth

Paul Van Mulbregt

A computer-implemented method is presented. The method comprises sequentially receiving a plurality of utterance prefixes, each sequentially received utterance prefix derived from a progressively longer incomplete portion of a full user utterance. For each sequentially received utterance prefix, a complete dataflow program is predicted based on the utterance prefix. The complete dataflow program includes a plurality of program nodes to be executed to satisfy the full user utterance. One or more program nodes are selected from the predicted complete dataflow program to speculatively execute based on at least the utterance prefix.

Speculative execution of dataflow program nodes

A method of automatically delineating turns in a multi-turn dialogue between a user and a conversational computing interface. Audio data encoding speech of the user in the multi-turn dialogue is received. The audio data is analyzed to recognize, in the speech of the user, an utterance followed by a silence. The utterance is recognized as a last utterance in a turn of the multi-turn dialogue responsive to the silence exceeding a context-dependent duration dynamically updated based on a conversation history of the multi-turn dialogue and features of the received audio, wherein the conversation history includes one or more previous turns of the multi-turn dialogue taken by the user and one or more previous turns of the multi-turn dialogue taken by the conversational computing interface.

Automatic turn delineation in multi-turn dialogue

An interaction assistant conducts multiple turn interaction dialogs with a user in which context is maintained between turns, and the system manages the dialog to achieve an inferred goal for the user. The system includes a linguistic interface to a user and a parser for processing linguistic events from the user. A dialog manager of the system is configured to receive alternative outputs from the parser, and selecting an action and causing the action to be performed based on the received alternative outputs. The system further includes a dialog state for an interaction with the user, and the alternative outputs represent alternative transitions from a current dialog state to a next dialog state. The system further includes a storage for a plurality of templates, and wherein each dialog state is defined in terms of an interrelationship of one or more instances of the templates.

Iteratively updating parameters for dialog states

Automated assistant for user interaction via speech

Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture.

Configurable speech recognition system using multiple recognizers

Configurable speech recognition system using a pronunciation alignment between multiple recognizers

Methods and apparatus for unsupervised wakeup of a device including receiving a first acoustic event at a first time and a second acoustic event at a second time, wherein the first and second acoustic events have scores above a first threshold identifying the first and second acoustic events as wakeup candidates for a wakeup phrase for an unsupervised wakeup of a device. It can be determined that the first acoustic event score is below a second threshold, which is higher than the first threshold and whether a difference between the first and second times is within a range to check for correlation in time between the first and second acoustic events. Occurrence of a wakeup event can be determined based upon the first and second times.

Methods and apparatus for unsupervised wakeup with time-correlated acoustic events

Methods and apparatus for unsupervised wakeup of a device including receiving a first acoustic event at a first time and a second acoustic event at a second time, wherein scores of the first and second acoustic events are above a first threshold identifying the first and second acoustic events as wakeup candidates for a wakeup phrase for an unsupervised wakeup of a device. It is determined that the first acoustic event is above a second threshold, which is higher than the first threshold, and that the second acoustic event is above a third threshold, which is higher than the first threshold. Occurrence of a wakeup event can be determined based upon acoustic similarity of the events.

Methods and apparatus for unsupervised wakeup

Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture. An indication of the availability of the remote speech recognition to perform speech recognition at a point in time may be provided to a user of the client device via a user interface of the client device.

Techniques disclosed herein include systems and methods that enable a voice trigger that wakes-up an electronic device or causes the device to make additional voice commands active, without manual initiation of voice command functionality. In addition, such a voice trigger is dynamically programmable or customizable. A speaker can program or designate a particular phrase as the voice trigger. In general, techniques herein execute a voice-activated wake-up system that operates on a digital signal processor (DSP) or other low-power, secondary processing unit of an electronic device instead of running on a central processing unit (CPU). A speech recognition manager runs two speech recognition systems on an electronic device. The CPU dynamically creates a compact speech system for the DSP. Such a compact system can be continuously run during a standby mode, without quickly exhausting a battery supply.

Embedded system for construction of small footprint speech recognition with user-definable constraints

A method for speech recognition. The method uses a single pronunciation estimator to train acoustic phoneme models and recognize utterances from multiple languages. The method includes accepting text spellings of training words in a plurality of sets of training words, each set corresponding to a different one of a plurality of languages. The method also includes, for each of the sets of training words in the plurality, receiving pronunciations for the training words in the set, the pronunciations being characteristic of native speakers of the language of the set, the pronunciations also being in terms of subword units at least some of which are common to two or more of the languages. The method also includes training a single pronunciation estimator using data comprising the text spellings and the pronunciations of the training words.

Multilingual speech recognition

The subject innovation provides a system and/or a method that facilitates developing schemas for a file storage system. A type definition component can provide a schema grammar, wherein a generator component can employ the schema grammar to build the schema for the file storage system. The schema grammar can describe information types stored in the file storage system that are represented as instances of complex types that are part of a type system that supports inheritance. The schema grammar can support a declaration of an association between types, versioning specifications, and/or content indexing specifications.

Schema grammar and compilation

Growing community of inventors

Somerville, MA, United States of America

Michael Jack Newman