Abstract: Embodiments of systems and methods for user enrollment in speaker authentication and speaker identification systems are disclosed. In some embodiments, the enrollment process includes collecting speech samples that are examples of multiple speech types spoken by a user, computing a speech representation for each speech sample, and aggregating the example speech representations to form a robust overall representation or user voiceprint of the user's speech.

Abstract: A multi-factor identification system is provided in which enrolled user authentication information is updated in the course of an authorization request based upon at least one of a confidence level of a match between a request first factor identifier, produced based upon first unique user identifying information received with the authentication request, and a respective matching enrolled first factor identifier and a confidence level of a match between a request second factor identifier, produced based upon second unique user identifying information received with the authentication request, and a respective matching enrolled second factor identifier.

Abstract: An audio signal encoding method is provided comprising: receiving first and second audio signal frames; processing a second portion of the first audio signal frame and a first portion of the second audio signal frame using an orthogonal transformation to determine in part a first intermediate encoding result; and processing the first intermediate encoding result using an orthogonal transformation to determine a set of spectral coefficients that corresponds to at least a portion of the first audio signal frame.

Abstract: An audio signal encoding method is provided comprising: receiving first and second audio signal frames; processing a second portion of the first audio signal frame and a first portion of the second audio signal frame using an orthogonal transformation to determine in part a first intermediate encoding result; and processing the first intermediate encoding result using an orthogonal transformation to determine a set of spectral coefficients that corresponds to at least a portion of the first audio signal frame.

Abstract: A method of encoding an audio signal is provided comprising: applying multiple different time-frequency transformations to an audio signal frame; computing measures of coding efficiency across multiple frequency bands for multiple time-frequency resolutions; selecting a combination of time-frequency resolutions to represent the frame at each of the multiple frequency bands based at least in part upon the computed measures of coding efficiency; determining a window size and a corresponding transform size; determining a modification transformation; windowing the frame using the determined window size; transforming the windowed frame using the determined transform size; modifying a time-frequency resolution within a frequency band of the transform of the windowed frame using the determined modification transformation.

Abstract: Embodiments of systems and methods are described for estimating a position of a loudspeaker and notifying a listener if an abnormal condition is detected, such as an incorrect loudspeaker orientation or an obstruction in a path between the loudspeaker and a microphone array. For example, a front component of a multi-channel surround sound system may include the microphone array and a position estimation engine. The position estimation engine may estimate the distance between the loudspeaker and the microphone array. In addition, the position estimation engine may estimate an angle of the loudspeaker using a first technique. The position estimation engine may also estimate an angle of the loudspeaker using a second technique. The two angles can be processed to determine whether the abnormal condition exists. If the abnormal condition exists, a listener can be notified and be provided with suggestions for resolving the issue in a graphical user interface.

Abstract: A method to decode audio signals is provided that includes: receiving an input spatial audio signal; determining directions of arrival of directional audio sources represented in the received input spatial audio signal; determining one of an active input spatial audio signal component and a passive spatial audio signal input component, based upon the determined directions of arrival; determining the other of the active input spatial audio signal component and the passive input spatial audio signal component based upon the determined one of the active input spatial audio signal component and the passive input spatial audio signal component; decoding the active input spatial audio signal component to a first output format; and decoding the passive input spatial audio signal component to a second output format.

Abstract: Embodiments of systems and methods for adaptive sound equalization in personal hearing devices are disclosed. In some embodiments a microphone in a personal hearing device receives sound from the listener's environment. The sound then is analyzed to determine one or more desired targets, for instance loudness level or spectral balance. The determined targets then are used to control adaptive processing of the sound received by the microphone to generate a perceptually improved sound to render to the listener.

Abstract: A method comprises: receiving an image of a real-world environment; using a machine learning classifier, classifying the image to produce classifications associated with acoustic presets for an acoustic environment simulation, the acoustic presets each including acoustic parameters that represent sound reverberation; and selecting an acoustic preset among the acoustic presets based on the classifications.

Abstract: A method to encode audio signals is provided for use with an audio capture device that includes multiple microphones having a spatial arrangement on the device, a method to encode audio signals comprising: receiving multiple microphone signals corresponding to the multiple microphones; determining a number and directions of arrival of directional audio sources represented in the one or more microphone signals; determining one of an active microphone signal component and a passive microphone signal component, based upon the determined number and directions of arrival; determining the other of the active microphone signal component and the passive microphone signal component, based upon the determined one of the active input spatial audio signal component and the passive input spatial audio signal component; encoding the active microphone signal component; encoding the passive microphone signal component.

Abstract: Embodiments of systems and methods are described for reducing undesired leakage energy produced by a non-front-facing speaker in a multi-speaker system. For example, the multi-speaker system can include an array of forward-facing speakers, one or more upward-facing speakers, and/or one or more side-facing speakers. Filters coupled to any two of the speakers in the multi-speaker system can generate audio signals output by the coupled speakers to reduce, attenuate, or cancel a portion of an audio signal output by one or more non-front-facing speakers that acoustically propagates along a direct path from the respective non-front-facing speaker to a listening position in a listening area in front of the multi-speaker system.

Abstract: A multi-factor identification system is provided in which enrolled user authentication information is updated in the course of an authorization request based upon at least one of a confidence level of a match between a request first factor identifier, produced based upon first unique user identifying information received with the authentication request, and a respective matching enrolled first factor identifier and a confidence level of a match between a request second factor identifier, produced based upon second unique user identifying information received with the authentication request, and a respective matching enrolled second factor identifier.

Abstract: Deep-learning classifier training systems and methods for training a classification system based on machine learning are disclosed. In some embodiments the training is configured to form classification regions of a specified shape. In some embodiments the training is configured to form classification regions in accordance with specified classification criteria. The systems and methods disclosed for training a classification system lead to improved inference performance.

Abstract: Embodiments of systems and methods for user enrollment in speaker authentication and speaker identification systems are disclosed. In some embodiments, the enrollment process includes collecting speech samples that are examples of multiple speech types spoken by a user, computing a speech representation for each speech sample, and aggregating the example speech representations to form a robust overall representation or user voiceprint of the user's speech.

Abstract: An audio signal encoding method is provided comprising: receiving first and second audio signal frames; processing a second portion of the first audio signal frame and a first portion of the second audio signal frame using an orthogonal transformation to determine in part a first intermediate encoding result; and processing the first intermediate encoding result using an orthogonal transformation to determine a set of spectral coefficients that corresponds to at least a portion of the first audio signal frame.

Abstract: A method of encoding an audio signal is provided comprising: applying multiple different time-frequency transformations to an audio signal frame; computing measures of coding efficiency across multiple frequency bands for multiple time-frequency resolutions; selecting a combination of time-frequency resolutions to represent the frame at each of the multiple frequency bands based at least in part upon the computed measures of coding efficiency; determining a window size and a corresponding transform size; determining a modification transformation; windowing the frame using the determined window size; transforming the windowed frame using the determined transform size; modifying a time-frequency resolution within a frequency band of the transform of the windowed frame using the determined modification transformation.

Abstract: Embodiments of systems and methods are described for reducing undesired leakage energy produced by a non-front-facing speaker in a multi-speaker system. For example, the multi-speaker system can include an array of forward-facing speakers, one or more upward-facing speakers, and/or one or more side-facing speakers. Filters coupled to any two of the speakers in the multi-speaker system can generate audio signals output by the coupled speakers to reduce, attenuate, or cancel a portion of an audio signal output by one or more non-front-facing speakers that acoustically propagates along a direct path from the respective non-front-facing speaker to a listening position in a listening area in front of the multi-speaker system.

Abstract: A method to decode audio signals is provided that includes: receiving an input spatial audio signal; determining directions of arrival of directional audio sources represented in the received input spatial audio signal; determining one of an active input spatial audio signal component and a passive spatial audio signal input component, based upon the determined directions of arrival; determining the other of the active input spatial audio signal component and the passive input spatial audio signal component based upon the determined one of the active input spatial audio signal component and the passive input spatial audio signal component; decoding the active input spatial audio signal component to a first output format; and decoding the passive input spatial audio signal component to a second output format.

Abstract: A method and a system for calibrating a surround sound system are disclosed. The calibration system can provide a graphical user interface for display comprising a visual representation of the room hosting a multichannel surround sound system. The graphical user interface can permit user input of gestures to place or make changes to the placement of icons representing one or more loudspeakers and a listener. The calibration system can estimate the positions of the one or more loudspeakers or the listener based on the placement of the icons in the model room. A spatial calibration based on the estimated positions can then be performed such that the multichannel surround sound system can render sound scenes more accurately.

Abstract: An audio signal encoding method is provided comprising: receiving first and second audio signal frames; processing a second portion of the first audio signal frame and a first portion of the second audio signal frame using an orthogonal transformation to determine in part a first intermediate encoding result; and processing the first intermediate encoding result using an orthogonal transformation to determine a set of spectral coefficients that corresponds to at least a portion of the first audio signal frame.