Abstract: One embodiment provides a computer-implemented method that includes utilizing text information obtained from a title of a media content item and a trainable model for improving accuracy for classification of the media content item. The trainable model is utilized using a sequence of text to numeric-vector embeddings for classification of the media content item. At least one of a word embedding model parameter or a latent semantic analysis dimension is jointly optimized using the text information, and a classifier model for maximizing accuracy of the classification of the media content item.

Abstract: One embodiment provides a computer-implemented method that includes implementing a customizable compressor for at least one sidechain processing associated with a loudspeaker. Machine learning is applied to automatically tune one or more parameters of the at least one sidechain processing. One or more channels are extracted, including a low-frequency effects (LFE) channel, for nonlinear signal synthesis. A proportional power-sum-based mix-in of an LFE sidechain channel is applied into a non-LFE sidechain. The LFE sidechain channel is maintained within a specified threshold of being level, before and after nonlinear signal synthesis.

Abstract: Acoustic echo cancellation for a video conference system is described. A location of a person in a room can be determined. An audio signal received from the location of the person can be captured using beamforming. An acoustic echo cancellation parameter can be determined based in part on the audio signal captured from the location of the person. Acoustic echo cancellation can be performed on the audio signal using the acoustic echo cancellation parameter.

Abstract: Embodiments are described for a method of rendering audio for playback through headphones comprising receiving digital audio content, receiving binaural rendering metadata generated by an authoring tool processing the received digital audio content, receiving playback metadata generated by a playback device, and combining the binaural rendering metadata and playback metadata to optimize playback of the digital audio content through the headphones.

Abstract: One embodiment provides a method comprising optimizing one or more stimuli parameters by applying machine learning to training data. The method further comprises determining, based on the one or more optimized stimuli parameters, stimuli for simultaneously exciting a plurality of speakers within a spatial area. The stimuli has a shortest possible duration that is accurate for simultaneous deconvolution of a plurality of impulse responses of the plurality of speakers. The method further comprises simultaneously exciting the plurality of speakers by providing the stimuli to the plurality of speakers at the same time for reproduction. The method further comprises simultaneously deconvolving the plurality of impulse responses based on the stimuli and one or more measurements of sound recorded during the reproduction and arriving at one or more microphones within the spatial area.

Abstract: One embodiment provides a method comprising determining stimuli for simultaneously exciting a plurality of speakers within a spatial area. The method further comprises simultaneously exciting the plurality of speakers by providing the stimuli to the plurality of speakers at the same time for reproduction. The method further comprises recording, during the reproduction, one or more measurements of sound arriving at one or more microphones within the spatial area. The method further comprises simultaneously deconvolving a plurality of impulse responses of the plurality of speakers based on the stimuli and the one or more measurements.

Abstract: Embodiments are described for a method of rendering audio for playback through headphones comprising receiving digital audio content, receiving binaural rendering metadata generated by an authoring tool processing the received digital audio content, receiving playback metadata generated by a playback device, and combining the binaural rendering metadata and playback metadata to optimize playback of the digital audio content through the headphones.

Abstract: In example implementations, an apparatus is provided. The apparatus includes an adaptive filter and a double talk detector in communication with the adaptive filter. The adaptive filter is to calculate a transfer function with coefficients for a particular time that is applied to an output signal of a microphone to cancel echoes caused by a reference signal in the output signal of the microphone. The double talk detector is to determine a peak of the coefficients, detect double talk based on a location of the peak of the coefficients, and transmit a pause signal to the adaptive filter in response to detection of the double talk, wherein the pause signal is to pause a calculation of updates to the coefficients by the adaptive filter.

Abstract: In one example in accordance with the present disclosure, a system is described. The system includes a processor to perform spatial audio processing on a received audio signal and an audio interface to connect an audio output device to a computing device. The system also includes a controller. The controller determines a spatial audio processing capability of the audio output device and disables spatial audio processing on one of the audio output device and the processor based on a determination of the spatial audio processing capability of the audio output device.

Abstract: In one example in accordance with the present disclosure, a system is described. The system includes a decompose device to decompose a multi-channel audio stream into at least a first portion and a second portion. A synthesis device of the system independently synthesizes harmonics in each of the first portion and the second portion using different harmonic models. An audio generator of the system combines synthesized harmonics from the first portion and the second portion with the multi-channel audio stream to generate a synthesized audio output.

Abstract: According to examples, an apparatus may include a processor and a non-transitory computer readable medium on which is stored instructions that the processor may execute to access an audio signal captured by a microphone of a user's speech while the microphone is in a muted state. The processor may also execute the instructions to analyze a spectral or frequency content of the accessed audio signal to determine whether the user was facing the microphone while the user spoke. In addition, based on a determination that the user was facing the microphone while the user spoke, the processor may execute the instructions to unmute the microphone.

Abstract: In some examples, an audio control system can include a first set of resources, a second set of resources and a controller. The first set of resources can generate a frequency energy band representation of a multi-channel source audio input. Additionally, the second set of resources can determine at least a value representing a strength of correlation between multiple channels of the multi-channel source audio input. Moreover, the audio output controller can determine a set of control parameters for tuning sound creation from an audio signal generator to reflect a set of spatial characteristics of the source audio input, based on the frequency energy band representation and the first value.

Abstract: One embodiment provides a method comprising determining stimuli for simultaneously exciting a plurality of speakers within a spatial area. The method further comprises simultaneously exciting the plurality of speakers by providing the stimuli to the plurality of speakers at the same time for reproduction. The method further comprises recording, during the reproduction, one or more measurements of sound arriving at one or more microphones within the spatial area. The method further comprises simultaneously deconvolving a plurality of impulse responses of the plurality of speakers based on the stimuli and the one or more measurements.

Abstract: One embodiment provides a computer-implemented method that includes implementing a customizable compressor for at least one sidechain processing associated with a loudspeaker. Machine learning is applied to automatically tune one or more parameters of the at least one sidechain processing. One or more channels are extracted, including a low-frequency effects (LFE) channel, for nonlinear signal synthesis. A proportional power-sum-based mix-in of an LFE sidechain channel is applied into a non-LFE sidechain. The LFE sidechain channel is maintained within a specified threshold of being level, before and after nonlinear signal synthesis.

Abstract: In some examples, immersive audio rendering may include determining whether an audio signal includes a first content format including stereo content, or a second content format including multichannel or object-based content. In response to a determination that the audio signal includes the first content format, the audio signal may be routed to a first block that includes a low-frequency extension and a stereo to multichannel upmix to generate a resulting audio signal. Alternatively, the audio signal may be routed to another low-frequency extension to generate the resulting audio signal. The audio signal may be further processed by performing spatial synthesis on the resulting audio signal, and crosstalk cancellation on the spatial synthesized audio signal. Further, multiband-range compression may be performed on the crosstalk cancelled audio signal, and an output stereo signal may be generated based on the multiband-range compressed audio signal.

Abstract: Embodiments are described for a method of rendering audio for playback through headphones comprising receiving digital audio content, receiving binaural rendering metadata generated by an authoring tool processing the received digital audio content, receiving playback metadata generated by a playback device, and combining the binaural rendering metadata and playback metadata to optimize playback of the digital audio content through the headphones.

Abstract: In some examples, adaptive speech intelligibility control for speech privacy may include determining, based on background noise at a near-end of a speaker, a noise estimate associated with speech emitted from the speaker, and comparing, by using a specified factor, the noise estimate to a speech level estimate for the speech emitted from the speaker. Adaptive speech intelligibility control for speech privacy may further include determining, based on the comparison, a gain value to be applied to the speaker to produce the speech at a specified level to maintain on-axis intelligibility with respect to the speaker, and applying the gain value to the speaker.

Abstract: A communication system may include, in an example, a first computing device communicatively coupled, via a network, to at least a second computing device maintained at a geographically distinct location than the first computing device; the first computing device including: an array of audio output devices and a processor to receive transmitted speech data and metadata describing an estimated direction of arrival (DOA) of speech from a plurality of speakers at an array of microphones at the second computing device and render audio at the array of audio output devices associated with the first computing device by eliminating spatial collision during rendering; said spatial collision arising due to the low angular separation of the estimated DOA of a plurality of speakers.

Abstract: An audio control system may include an imaging sensor to capture an image of an environment containing loudspeakers connected to the audio control system. A listening position subsystem may process the captured image to identify a listening position within the environment. A speaker position subsystem may process the captured image to determine a physical location of each loudspeaker relative to the identified user listening position. A signal processing subsystem may modify an output signal driving the loudspeakers to steer a soundfield generated by the loudspeakers. The audio control system may include a processor, memory, and/or hardware components to implement the various subsystems such that, at the identified user listening position, a perceived location of one of the loudspeakers is mapped to a location that is different than its physical location.

Abstract: A communication system may include, in an example, a first computing device communicatively coupled, via a network, to at least a second computing device maintained at a geographically distinct location than the first computing device; the first computing device including: an array of audio output devices and a processor to receive transmitted speech data and metadata describing an estimated direction of arrival (DOA) of speech from a plurality of speakers at an array of microphones at the second computing device and render audio at the array of audio output devices associated with the first computing device by eliminating spatial collision during rendering; said spatial collision arising due to the low angular separation of the estimated DOA of a plurality of speakers.