Google Inc.

Motorola Mobility LLC

Motorola Corporation

Google Technology Holdings LLC

Jincheng Wu

Joel A Clark

Plamen A Ivanov

Robert A Zurek

Adrian M Schuster

Pratik Kamdar

Fu-Lin Shau

Kevin J Bastyr

Snehitha Singaraju

Joseph C Dwyer

Rivanaldo S Oliveira

Malay Gupta

Mark A Jasiuk

Tenkasi Vaideeswaran Ramabadran

Sanjay N Kadiwala

Juan C Garcia

Kevin J Bastry

A device performs a method for using image data to aid voice recognition. The method includes the device capturing image data of a vicinity of the device and adjusting, based on the image data, a set of parameters for voice recognition performed by the device. The set of parameters for the device performing voice recognition include, but are not limited to: a trigger threshold of a trigger for voice recognition; a set of beamforming parameters; a database for voice recognition; and/or an algorithm for voice recognition. The algorithm may include using noise suppression or using acoustic beamforming.

Method and apparatus for using image data to aid voice recognition

A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.

Apparatus and method for power efficient signal conditioning for a voice recognition system

A device performs a method for using image data to aid voice recognition. The method includes the device capturing () image data of a vicinity of the device and adjusting (), based on the image data, a set of parameters for voice recognition performed by the device (). The set of parameters for the device performing voice recognition include, but are not limited to: a trigger threshold of a trigger for voice recognition; a set of beamforming parameters; a database for voice recognition; and/or an algorithm for voice recognition. The algorithm may include using noise suppression or using acoustic beamforming.

A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector on the audio signal in response to the detected change where the voice activity detector is the at least one signal processing component. The method may further include activating and running the noise suppressor only if a noise estimator determines that noise suppression is required. The method may activate and runs a noise type classifier to determine the noise type based on information received from the noise estimator and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.

A method, a system, and a computer program product for preventing initiation of a voice recognition session. The method includes monitoring at least one audio output channel for at least one audio trigger phrase that initiates a voice recognition session. The method further includes in response to detecting the at least one audio trigger phrase on the at least one audio output channel, setting a logic state of at least one output trigger detector of the at least one audio output channel to a first state. The method further includes gating a logic state of at least one input trigger detector of at least one audio input channel to the first state for a time period and preventing initiation of a voice recognition session by the at least one audio trigger phrase on the at least one audio input channel while the logic state is the first state.

Preventing initiation of a voice recognition session

A method, a system, and a computer program product for detecting an audio trigger phrase at a particular audio input channel and initiating a voice recognition session. The method includes capturing audio content by a plurality of microphone pairs of an audio capturing device, wherein each microphone pair of the plurality of microphone pairs is associated with an audio input channel of a plurality of audio input channels of the audio capturing device. The method further includes simultaneously monitoring, by a processor of the audio capturing device, audio content on each of the audio input channels. The method further includes: independently detecting, by the processor, an audio trigger phrase on at least one audio input channel of the plurality of audio input channels; and in response to detecting the audio trigger phrase, commencing a voice recognition session using the at least one audio input channel as an audio source.

Detecting audio trigger phrases for a voice recognition session

A method, a system, and a computer program product reducing noise in audio received by at least one microphone. The method includes determining, from an audio signal received by at least one primary microphone of an electronic device, whether a user that is proximate to the electronic device is currently speaking. The method further includes, in response to determining that a user is not currently speaking, receiving a first audio using a first microphone subset from among a plurality of microphones and receiving at least one second audio using at least one second microphone subset from among the plurality of microphones. The method further includes generating a composite signal from the first audio and the second audio. The method further includes collectively processing the audio signal and the composite signal to generate a modified audio signal having a reduced level of noise.

Reducing noise in audio signals

A method for controlling echo of a voice recognition system includes receiving at least two audio input signals corresponding to sound sensed by at least two microphones in a physical space. A first audio input signal of the at least two audio input signals is received on a primary channel, and each remaining audio input signal is received through a respective secondary channel. The method includes selecting, by a processor, based on an echo power level of a speaker in the physical space, a subset of echo control functions (ECFs) from among a plurality of ECFs of a multistage echo control system. Each ECF modifies the at least two audio input signals to reduce echo. The method includes generating a corresponding number of audio output signals by processing the signals received on the primary and secondary channels through the selected subset of ECFs, and outputting the audio output signals.

Pre-selectable and dynamic configurable multistage echo control system for large range level of acoustic echo

A method includes obtaining, by a processor, an audio echo signal and an audio desired signal from an acoustic echo correction stage of an electronic device, and converting the echo signal and the desired signal to the frequency domain. The method further includes grouping, by the processor, frequency bin results of respective frequency domain converted echo and desired signals into respective echo and desired sub-bands. A sub-band suppressor gain is estimated based on an estimated sub-band energy for the echo and desired sub-bands. The method further includes modulating the frequency domain converted desired signal to compensate for residual echo, the modulating based, at least in part, on the estimated sub-band suppressor gain, and the modulating producing a compensated frequency domain converted echo signal. The method also includes converting the compensated frequency domain converted desired signal into time domain converted audio output signal.

Echo cancellation and suppression in electronic device

A portable device performs echo cancellation and echo suppression. An audio echo signal and an audio desired signal are obtained from an acoustic echo correction stage of the portable device. The echo and desired signals are converted to the frequency domain. Frequency bin results of the respective frequency domain converted echo and desired signals are grouped into echo and desired sub-bands. A sub-band suppressor gain is estimated based on the estimated sub-band energy for the echo and desired sub-bands. The frequency domain converted echo signal is modulated based at least in part on the estimated sub-band suppressor gain to compensate for residual echo. The compensated frequency domain converted echo signal is time domain converted into an audio output signal. The audio output signal is processed by a selected one of a voice recognition engine and a communication module transmitter.

A method includes cycling through a plurality of microphone and speaker combinations in a mobile device in response to the mobile device being placed in speakerphone mode. The mobile device includes a plurality of microphones and at least one speaker. The method obtains acoustic echo data from an echo canceller for each microphone and speaker combination, calculates an acoustic isolation value for each combination and then selects a microphone and speaker combination based on the acoustic isolation value. The method may also include determining an echo spectrum for each microphone and speaker combination using the obtained acoustic echo data, and select an echo control profile based on a characteristic of the echo spectrum. The echo control profile is selected to further improve acoustic isolation for the selected microphone and speaker combination.

Apparatus with adaptive acoustic echo control for speakerphone mode

A device performs a method for using image data to aid voice recognition. The method includes the device capturing image data of a vicinity of the device and adjusting, based on the image data, a set of parameters for voice recognition performed by the device. The set of parameters for the device performing voice recognition include, but are not limited to: a trigger threshold of a trigger for voice recognition; a set of beamforming parameters; a database for voice recognition; and/or an algorithm for voice recognition, wherein the algorithm can include using noise suppression or using acoustic beamforming.

Growing community of inventors

Naperville, IL, United States of America

Jincheng Wu