Abstract: An audio signal outputting method includes: in a case where a first audio signal is output through a first device, receiving a first input of a user that is used to trigger a terminal device to output a second audio signal; and in response to the first input, outputting the first audio signal through a second device, and outputting a second audio signal through a third device. The first audio signal and the second audio signal are audio signals generated by different applications in the terminal device. The first device is any one of the terminal device and the at least one audio device, and the second device and the third device are any two of the terminal device and the at least one audio device.

Abstract: Example apparatus disclosed herein compare one or more audio latency characteristics with one or more audio latency requirements in response to detection of an audio silence event, the audio latency characteristic(s) associated with at least one of a hardware layer or a device layer of an audio stack of a compute device, the audio latency requirement(s) associated with an application. Disclosed example apparatus also control a device layer of the audio stack to enter a device layer low power mode in response to a first determination that the audio latency requirement(s) is/are met by the audio latency characteristic(s). Disclosed example apparatus further control a hardware layer of the audio stack to enter a hardware layer low power mode in response to the first determination and a second determination that an operation condition for entry into the hardware layer low power mode is met.

Abstract: A signal processing method comprises comparing a first frequency domain representation of a sequence of power values for respective windows of source input samples of a source input signal with a second frequency domain representation of a sequence of power values for respective windows of target input samples of a target input signal so as to generate a frequency domain difference representation; inverse-frequency-transforming the frequency domain difference representation to generate a modification indication; and applying the modification indication to the source input samples to generate respective output samples of an output signal.

Abstract: This application provide an audio detection method performed by a computer device. The method includes: acquiring a target time point and a reference point of the target time point from target audio data; performing energy evaluation on the target time point according to an audio amplitude value of the target time point to obtain an energy evaluation value of the target time point; performing energy evaluation on the reference point according to an audio amplitude value of the reference point to obtain an energy evaluation value of the reference point; performing accuracy verification on the target time point according to the energy evaluation value of the target time point and the energy evaluation value of the reference point; and if the accuracy verification on the target time point succeeds, adding the target time point as a target stress point into a target stress point set.

Abstract: Provided are an information processing apparatus, an information processing method, and a video sound output system that execute an output process of an acoustic signal in synchronization with a video signal. The information processing apparatus includes a control section that detects a position of a sound source appearing in a video displayed on a screen of a display unit and that uses one or more vibrators to vibrate the display unit and thereby control output of sound such that a sound image of sound in synchronization with the video is localized at the position where the sound source appears on the screen displaying the video. In a case of displaying videos of two or more video sources on individual windows, the control section localizes a sound image of a sound source detected from the video of each video source at a position where the sound source appears in the corresponding window.

Abstract: An electronic device comprising circuitry configured to analyze the results of a stereo or multi-channel source separation to determine one or more time-varying parameters, and to create spatially dynamic audio objects based on the one or more time-varying parameters.

Abstract: A skip behavior analyzer is part of a media delivery system that allows for unbiased A/B testing of a plurality of versions of a song. The media delivery system stores a plurality of versions of a song and randomly selects, for each requesting device, a version of the song to associate with that device. Each time the device requests the song, thereafter, the media delivery system will provide the same version of the song for consistency. The media delivery system then gathers song play and skip information, calculates the differences in distribution of the skip behavior, and provides the skip information to allow a music composer to better determine which version of a song is more popular and why that is so.

Abstract: The embodiments of the disclosure provide a method for adjusting a noise cancellation mode, an electronic device, and a computer readable storage medium. The method includes: estimating a noise perception indicator corresponding to an environmental noise; and adjusting a noise cancellation mode of an wearable audio device according to the noise perception indicator.

Abstract: A method for encoding an audio signal includes obtaining an ITD value of a current frame of an audio signal; obtaining a characteristic parameter of the current frame, wherein the characteristic parameter comprises at least one of a signal-to-noise ratio of the current frame or a peak feature of cross-correlation coefficients of the current frame; determining, based on the characteristic parameter, whether to use the initial ITD value as the finalized ITD value of the current frame; and encoding the current frame based on the finalized ITD value of the current frame, wherein if the initial ITD value is determined as not used as the finalized ITD value of the current frame, the finalized ITD value of the current frame is the same as a finalized ITD value of a previous frame of the current frame.

Abstract: A musician collaboration system includes a memory configured to store instructions and a processor configured to execute the instructions to: receive a request for providing a feature. The request including receiving a first content file associated with the feature; transmitting a message informing the request; one of transmitting an acceptance of the request and a denial of the request; and upon the acceptance of the request, receiving and transmitting a second content file including a version of the feature.

Abstract: Various implementations include a computational architecture for a personal active noise reduction (ANR) device. The device includes a communication interface that receives an audio stream, a driver, a microphone system and an ANR processing platform. The platform includes a first DSP configured to: receive the audio stream and signals from the microphone system, perform ANR on the audio stream according to a set of parameters in the first DSP, and output a processed audio stream. The platform includes a second DSP configured to: generate state data in response to an analysis of the source audio stream, signals from the microphone system, and the processed audio stream; and alter the operational parameters on the first DSP. The platform includes a general purpose processor configured to characterize a malfunction in response to instability or error condition events detected by the second DSP.

Abstract: A system processes an audio signal using spectrally orthogonal sound components. The system includes a circuitry that generates a mid component and a side component from a left channel and a right channel of the audio signal. The circuitry generates a hyper mid component including spectral energy of the side component removed from spectral energy of the mid component. The circuitry filters the hyper mid component, such as to provide spatial cue processing including panning or binaural processing, dynamic range processing, or other types of processing. The circuitry generates a left output channel and a right output channel using the filtered hyper mid component.

Abstract: The information processing device includes an acquisition unit, a determination unit, and a signal processing unit. The acquisition unit acquires one or a plurality of other sound elements. The determination unit determines importance levels of the sound elements acquired by the acquisition unit. The signal processing unit changes a sound source position of at least one of a sound element of a content being reproduced or another sound element according to the importance levels of the sound elements determined by the determination unit. Consequently, even in a case where the sound element of the reproduced content and the another sound element are simultaneously generated, sound interference between the sound element of the reproduced content and the another sound element can be suppressed.

Abstract: A head-worn sound reproduction device is provided in the form of left and right earphones, which can either be clipped to each ear or mounted on other headgear. The earphones deliver high fidelity audio to a user's eardrums from near-ear range, in a lightweight form factor that is fully “non-blocking” (allows coupling in and natural hearing of ambient sound). Each earphone has a woofer component that produces bass frequencies, and a tweeter component that produces treble frequencies. The woofer outputs the bass frequencies from a position close to the ear canal, while the tweeter outputs treble frequencies from a position that is either close to the ear canal or further away. In certain embodiments, the tweeter is significantly further from the ear canal than the woofer, leading to a more expansive perceived “sound stage”, but still with a “pure” listening experience.

Abstract: The present disclosure relates to methods, apparatus and systems for encoding an audio signal into a bitstream, in particular at an encoder, comprising: encoding or including audio signal data associated with 3DoF audio rendering into one or more first bitstream parts of the bitstream, and encoding or including metadata associated with 6DoF audio rendering into one or more second bitstream parts of the bitstream. The present disclosure further relates to methods, apparatus and systems for decoding an audio signal and audio rendering based on the bitstream.

Abstract: Implementations disclosed herein are directed to ephemeral learning of machine learning (“ML”) model(s) based on gradient(s) generated at a remote system (e.g., remote server(s)). Processor(s) of the remote system can receive stream(s) of audio data capturing spoken utterance(s) from a client device of a user. A fulfillment pipeline can process the stream(s) of audio data to cause certain fulfillment(s) of the spoken utterance(s) to be performed. Meanwhile, a training pipeline can process the stream(s) of audio data to generate gradient(s) using unsupervised learning techniques. Subsequent to the processing by the fulfillment pipeline and/or the training pipeline, the stream(s) of audio data are discarded by the remote system. Accordingly, the ML model(s) can be trained at the remote system without storing or logging of the stream(s) of audio data by non-transient memory thereof, thereby providing more efficient training mechanisms for training the ML model(s) and also increasing security of user data.

Abstract: A sound signal downmix method includes an inter-channel relationship information obtaining step of obtaining an inter-channel correlation value and an inter-channel time difference in an approximate manner, and a downmix step of obtaining a downmix signal based on the obtained information. In the inter-channel relationship information obtaining step, multiple channel signals are sorted such that signals of adjacent channels are similar to each other, the inter-channel correlation value and the inter-channel time difference are determined only between adjacent channels after the sorting, the inter-channel correlation value between non-adjacent channels is obtained by determining a value that has a monotonically non-decreasing relationship with the inter-channel correlation between the adjacent channels, and the inter-channel time difference between non-adjacent channels is obtained by adding up the inter-channel time differences of adjacent channels.

Abstract: A computer implemented method for training a machine learning model for audio compensation includes: receiving 3D models of a plurality of rooms, each of the 3D models comprising at least one sound source and at least one acoustic property; receiving a plurality of impulse responses at a listening position in each of the plurality of rooms, training the machine learning model for audio compensation using at least the plurality of impulse responses as input. Methods and systems using the disclosed computer implemented method and its features are also disclosed.

Abstract: Systems, devices, apparatuses, components, methods, and techniques for automatically generating media previews are provided. An example media system for automatically generating media previews for a particular artist include a trailer generation application configured to receive input specifying an artist and duration of a trailer, automatically select clips from two or more media items by the artist, and automatically arrange and combine the clips into a media trailer for later playback.

Abstract: A mobile terminal and a control method are provided. The mobile terminal includes an audio codec and a control chip, where the audio codec has sound channel output pins, the control chip and the audio codec are electrically connected to each other, and the control chip is configured to output a voltage compensating signal to the audio codec in processes of enabling and disabling the audio codec, so that a direct current bias voltage of the sound channel output pins is 0V in the processes of enabling and disabling the audio codec.