A method for processing a voice signal by an electronic system to create a song is disclosed. The method comprises the steps in the electronic system of acquiring an input singing voice recording (11); estimating a musical key (15b) and a Tempo (15a) from the singing voice recording (11); defining a tuning control (16) and a timing control (17) able to align the singing voice recording (11) with the estimated musical key (15b) and Tempo (15a); applying the tuning control (16) and the timing control (17) to the singing voice recording (11) so that an aligned voice recording (20) is obtained. Next, the method comprises the step of generating an music accompaniment (23) as function of the estimated musical key (15b) and Tempo (15a) and an arrangement database (22) and mixing the aligned voice recording (20) and the music accompaniment (23) to obtain the song (12). A system a server and a device are also disclosed.

Embodiments described herein relate generally to systems comprising a display device, a display device-coupled computing platform, a mobile device in communication with the computing platform, and a content server in which methods and techniques of capture and/or processing of audiovisual performances are described and, in particular, description of techniques suitable for use in connection with display device connected computing platforms for rendering vocal performance captured by a handheld computing device.

A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.

A system, method and computer product for training a neural network system. The method comprises applying an audio signal to the neural network system, the audio signal including a vocal component and a non-vocal component. The method also comprises comparing an output of the neural network system to a target signal, and adjusting at least one parameter of the neural network system to reduce a result of the comparing, for training the neural network system to estimate one of the vocal component and the non-vocal component. In one example embodiment, the system comprises a U-Net architecture. After training, the system can estimate vocal or instrumental components of an audio signal, depending on which type of component the system is trained to estimate.

A musical system may include one or more storage media, at least one processor, one or more sensors corresponding to keys of a musical instrument, and a display. The storage media may be configured to store a set of instructions for modifying a music score for a user based on a performance level of the user. The at least one processor may be configured to communicate with the one or more storage media. When executing the set of instructions, the processor is directed to determine a user performance level of a user and provide a modified music score for the user based on the user performance level. The sensors may be configured to sense a motion of at least one key of the keys and generate a key signal accordingly. The display may be configured to display the modified music score.

An accompaniment sound generating device includes a specifier, an accompaniment sound generator, and an accompaniment sound outputter. The specifier specifies a plurality of musical performance parts for which accompaniment sounds are generated based on an input musical performance sound. The accompaniment sound generator generates the accompaniment sounds that belong to the plurality of specified musical performance parts for each musical performance sound. The accompaniment sound outputter outputs the accompaniment sounds generated for the plurality of musical performance parts with timing for generating the accompaniment sounds aligned with timing for generating musical performance sounds.

A method for adjusting accompaniment music is disclosed. The method transposes the musical key of at least one section of the accompaniment music such that a song will have different musical key transpositions for different sections of the accompaniment music, so that singers whose vocal ranges are narrow can sing songs after the adjustment.

Systems and methods for low latency audio data pipelines are disclosed. For example, a software enabled access point is established for direct wireless communication between a microphone device and an electronic device. Additionally, an audio data processing pipeline that bypasses default data processing of an operating system stack of the electronic device is utilized. The audio data processing pipeline includes minimal audio data processing that writes audio data directly to hardware components for output of corresponding audio.

An electronic musical instrument outputs synthesized lyrics of a song based on lyric data in accordance with operations by a user. One or more processors in electronic musical instrument generate voice synthesis data for a lyric of the song based on the lyric data for the song at a timing at which said lyric is supposed to be outputted regardless of whether or not a user operation of the operating unit is detected at said timing; when the user operation of the operating unit is detected at said timing, cause voice sound synthesized based on the generated voice synthesis data to be outputted; and when the user operation of the operating unit is not detected at said timing, cause the voice sound synthesized based on the generated voice synthesis data not to be outputted.

An interactive music audition method, apparatus and terminal are provided. The method includes: generating audition inquiry information according to audition requirement information, wherein the audition inquiry information includes a plurality of audition music options associated with the audition requirement information; generating a plurality of audition inquiry voices corresponding to the respective audition music options based on the audition inquiry information, and playing the generated audition inquiry voices; acquiring music selection information for the generated audition inquiry voices; and playing audition music according to the music selection information. Not only the interaction experience between a user and a smart device is improved, but also the accuracy of mining a user's interest is increased.