Voice command type entry used as a basis for applying “audio effects” (see definition herein), “sound effects” (see definition herein) and/or audio edits (see definition herein) to a sound signal. This may be done so that the various types of instructed audio processing evoke, in typical listeners, a desired sentiment or mood. Artificial intelligence may be used to accomplish this objective.

Digital signal processing and machine learning techniques can be employed in a vocal capture and performance social network to computationally generate vocal pitch tracks from a collection of vocal performances captured against a common temporal baseline such as a backing track or an original performance by a popularizing artist. In this way, crowd-sourced pitch tracks may be generated and distributed for use in subsequent karaoke-style vocal audio captures or other applications. Large numbers of performances of a song can be used to generate a pitch track. Computationally determined pitch trackings from individual audio signal encodings of the crowd-sourced vocal performance set are aggregated and processed as an observation sequence of a trained Hidden Markov Model (HMM) or other statistical model to produce an output pitch track.

A reproduction control method, which is executed by a computer, includes detecting a first state in which an object is separated from an operation surface by a prescribed distance and a second state in which the object is in contact with the operation surface, initiating sound reproduction at a first time point at which the first state is detected, continuing the sound reproduction from the first time point to a third time point which is subsequent to a second time point at which the second state is detected, and controlling a change in a feature amount of a sound during a first time period from the first time point to the second time point.

A method for editing an audio special effect includes that an audio input control, an audio playing control and an audio output control and at least one of an audio special effect control or an audio detection control are created based on a first creation operation triggered by a user; an audio output port of the audio input control is connected to an audio input port of the audio playing control, an audio output port of the audio playing control is connected to an audio input port of a second audio control, and an audio output port of the second audio control is connected to an input port of the audio output control; and an audio stream of to-be-processed audio is controlled to flow from the audio input control sequentially through the audio playing control, the second audio control and the audio output control to obtain target special effect audio.

Techniques have been developed to facilitate (1) the capture and pitch correction of vocal performances on handheld or other portable computing devices and (2) the mixing of such pitch-corrected vocal performances with backing tracks for audible rendering on targets that include such portable computing devices and as well as desktops, workstations, gaming stations, even telephony targets. Implementations of the described techniques employ signal processing techniques and allocations of system functionality that are suitable given the generally limited capabilities of such handheld or portable computing devices and that facilitate efficient encoding and communication of the pitch-corrected vocal performances (or precursors or derivatives thereof) via wireless and/or wired bandwidth-limited networks for rendering on portable computing devices or other targets.

An electronic musical instrument includes at least one processor that, in accordance with a user operation on an operation unit, obtains lyric data and waveform data corresponding to a first tone color; inputs the obtained lyric data to a trained model so as to cause the trained model to output acoustic feature data in response thereto; generates waveform data corresponding to a singing voice of a singer and corresponding to a second tone color that is different from the first tone color, based on the acoustic feature data outputted from the trained model and the obtained waveform data corresponding to the first tone color; and outputs a singing voice based on the generated waveform data corresponding to the second tone color.

Apparatus for outputting an audio signal in a vehicle cabin comprising: at least one audio outputting device configured to output an audio signal comprising at least one audio signal component containing a human voice, particularly a singer's voice, and/or a musical instrument in a vehicle cabin; at least one audio processing device configured to process at least one audio signal output by the at least one audio outputting device so as to suppress the audio signal component in a suppression mode; at least one audio receiving device configured to receive an acoustic human voice signal, of at least one person located in the vehicle cabin whilst the audio outputting device outputs the audio signal in the vehicle cabin; and a control device configured to control operation of the audio processing device based on at least one acoustic human signal received by the audio receiving device.

An electronic device having circuitry configured to perform source separation on an audio signal to obtain a separated source and a residual signal, to perform feature extraction on the separated source to obtain one or more processing parameters, and to perform audio processing on a captured audio signal based on the one or more processing parameters to obtain an adjusted separated source.

Disclosed herein are computer-implemented method, system, and computer-readable storage-medium embodiments for implementing template-based excerpting and rendering of multimedia performances technologies. An embodiment includes at least one computer processor configured to retrieve a first content instance and corresponding first metadata. The first content instance may include a first plurality of structural elements, with at least one structural element corresponding to at least part of the first metadata. The first content instance may be transformed by a rendering engine running on the at least one computer processor and/or transmitted to a content-playback device.

The implementation of modal processors, which involve the parallel combination resonant filters, may be costly for applications such as artificial reverberation that can require thousands of modes. In one embodiment, the input signal is decomposed into a plurality of subbands, the outputs of which are downsampled. In each downsampled band, resonant filters are applied at the downsampled sampling rate, and their output is upsampled and filtered to form the band output. In these and other embodiments, a feature of responses of the mode filters have been optimized to minimize an aspect of a residual error after a point in time.