Various embodiments provide techniques for generating real-time musical accompaniment for musical content included in an audio signal. A real-time musical accompaniment system receives the audio signal via an audio input device. The system extract, from the audio signal, musical information characterizing at least a portion of the musical content. The system generates musical information that has at least one of a rhythmic relationship and a harmonic relationship with the musical information. The system generates an output audio signal that is complementary to the musical information. The system transmits, substantially immediately after receiving the audio signal, the output audio signal to an audio output device.

A data generation device includes: an acquisition part configured to acquire measurement data that corresponds to measurement values, obtained in chronological order, corresponding to a behavior of a key or a member coordinating with the key for each of a plurality of keys; and a data generation part configured to generate display data for displaying a screen showing the measurement values corresponding to each of the plurality of keys along a time axis based on the acquired measurement data.

In at least one embodiment, a method of performing automatic transcription of musical content included in an audio signal received by a computing device is provided. The method includes processing, using the computing device, the received audio signal to extract musical information characterizing at least a portion of the musical content and generating, using the computing device, a plurality of musical notations representing alternative musical interpretations of the extracted musical information. The method further includes applying a selected one of the plurality of musical notations for transcribing the musical content of the received audio signal.

Techniques are provided for generating an output file. One technique involves the steps of generating audio or MIDI content blocks from one or more musical performances; receiving an input file having audio or MIDI music content; generating a harmonic chord map for the input file; using the harmonic chord map to automatically select a subset of the audio or MIDI content blocks, and generating the output file by combining the selected subset of content blocks and the input file. This technique may enable the creation of unique and new musical accompaniments by re-purposing audio or MIDI content from back catalogs and/or out-takes of musical works. The new arrangement may be provided in multiple music styles, genres, or moods and may contain performances from multiple musical instruments, which may be pre-recorded from live instrument performances and/or of MIDI generated musical content.

Systems and methods for mapping parts in a digital sheet music file for a harmony. The method may include receiving a selection of a music segment for part mapping, receiving a digital sheet music representation of the selected music segment, and determining a plurality of plausible part mapping for the digital sheet music representation. A part mapping identifies one or more distinct musical parts in the digital sheet music representation, each of said one or more distinct musical parts corresponding to a performer of the harmony. The method may also include analyzing one or more features of the plurality of plausible part mapping to identify a highest probability part mapping based on previously stored information, and outputting the highest probability part mapping.

A music piece analyzer includes: a beat interval acquiring unit configured to acquire a beat interval in music piece data; a candidate detector configured to detect sounding positions where a change amount for sounding is equal to or more than a predetermined threshold in the music piece data, as candidates for sounding positions of a snare drum; and a sounding position determination unit configured to determine that the candidates for the sounding positions at a two-beat interval acquired by the beat interval acquiring unit in the music piece data are the sounding positions of the snare drum, among the candidates for the sounding positions of the snare drum.

Audio data of an original work is received. Text in the audio data is translated to a target language. The audio data is passed to a first deep learning model to learn voice features in the audio data. The audio data is passed to a second deep learning model to learn audio properties in the audio data. The translated text is synchronized to play in the position of original text of the original work in a synthesized voice. A translated audio data of the original work is created by combining the synchronized translated text in the synthesized voice with music of the audio data.

According to embodiments of the present disclosure, systems, methods, and computer program products for audio- and video-editing are provided. A reference file comprising a visual representation (e.g., musical score) of a final video/audio product is read and displayed to a user. A plurality of sections (e.g., measures) and a plurality of symbols (e.g., notes) are determined. A plurality of audio/video recordings are read where each recording corresponding to at least a portion of the visual representation. For each of the plurality of sections, a corresponding segment of at least one of the plurality of audio/video recordings is determined. First selections of a section of the plurality of sections are received from the user. For each of the first selections, a listing of the plurality of audio/video recordings in which at least a portion of the selected section occurs is displayed to the user. For each of the first selections, a second selection of an audio/video recording from the listing is received from the user thereby linking the selected section to the corresponding segment of the selected audio/video recording. An audio/video file is generated by combining each of the linked segments.

A method for detecting a melody of an audio signal, including: dividing the audio signal into a plurality of audio segments based on a beat, detecting a pitch frequency of each frame of audio sub-signal in each of the audio segments, and estimating a pitch value of each of the audio segments based on the pitch frequency; determining a pitch name corresponding to each of the audio segments based on a frequency range of the pitch value; acquiring a musical scale of the audio signal by estimating a tonality of the audio signal based on the pitch name of each of the audio segments; and determining a melody of the audio signal based on a frequency interval of the pitch value of each of the audio segments in the musical scale.

A method and system for automatically transcribing an audio source, e.g. a WAV file or live feeds, into a computer-readable code, e.g., enhanced MIDI, are provided, specifically and limited to solving a central problem that has not been solved elsewhere: it takes a large sampling window, say from a fifth of a second to a full second for typical music, to extract many music perceptual parameters of interest, yet that transcription also needs to maintain synchronization with the source music, with the time resolution of that synchronization about a sixteenth of a second.