Abstract: A voice quality preference learning device according to an embodiment includes a storage, a user interface system, and a learning processor. The storage stores a plurality of acoustic models. The user interface system receives an operation input indicating a voice quality preference of a user for voice quality. The learning processor learns a preference model corresponding to the voice quality preference of the user based at least in part on the operation input, the operation input associated with a voice quality space, wherein the voice quality space is obtained by dimensionally reducing the plurality of acoustic models.

Abstract: A system and method to communicate between devices through natural language using instant messaging applications and interoperable public identifiers where the method comprises the stages of receiving an instant messaging module from an instant messaging client, an instant message in natural language, with an interoperable public identifier, identifying said message as a message to be processed because said interoperable public identifier corresponds to the public identifier that uniquely identifies said instant messaging module, processing said instant message and resending said message to a natural language processing module, processing the content of said message in said natural language processing module to translate said content into at least one specific command for a target device and launch the execution of the at least said command in said target device.

Abstract: Captured vocals may be automatically transformed using advanced digital signal processing techniques that provide captivating applications, and even purpose-built devices, in which mere novice user-musicians may generate, audibly render and share musical performances. In some cases, the automated transformations allow spoken vocals to be segmented, arranged, temporally aligned with a target rhythm, meter or accompanying backing tracks and pitch corrected in accord with a score or note sequence. Speech-to-song music applications are one such example. In some cases, spoken vocals may be transformed in accord with musical genres such as rap using automated segmentation and temporal alignment techniques, often without pitch correction. Such applications, which may employ different signal processing and different automated transformations, may nonetheless be understood as speech-to-rap variations on the theme.

Abstract: A method for combining first second audio tracks includes modifying at least one of the two audio tracks; and storing the first and the second audio track in a non-volatile medium, characterized in that the interbeat intervals of the modified first and the second audio track exhibit long-range cross-correlations (LRCC).

Abstract: Provided are a method and apparatus for generating and storing a database that may be searched for music upon a user's request, and a method and apparatus for searching for music corresponding to the user's request. According to an embodiment of the present invention, a plurality of melodies are divided based on phrase breaks and are stored, and a number of melodies which are similar to the user's request are detected from the stored melodies.

Abstract: A method and system for analyzing patterns in the relationships of notes of an input piece of music. The method comprises generating a set of the most frequently occurring note pitches in ascending pitch order that matches an interval pattern, and detecting out-of-key pitches that lie outside of this interval pattern. One or more potential key sequence bifurcations are identified which represent a list of possible key sequences according to forwards and backwards analysis. By finding patterns of repetition in the chordal sequences that may be generated according to these key sequence bifurcations, a key sequence that allows the most frequently recurring chord sequences may be chosen. Chord sequences may be analyzed by using ghost chords, temporary harmonic structures that are created, updated and finalized over time according to a combination of essential and inessential note fragments. The method further comprises identifying non-harmony pitches according to the analyzed chord sequence.

Abstract: Computer-based methods infer a metrical grid from music that has been input without a predetermined time signature or tempo, enabling such free rhythm input to be annotated with the inferred grid, and stored and transcribed as a musical score. The methods use Bayesian modeling techniques, in which an optimal metrical grid is inferred by identifying the metrical grid that best explains the given sequence of notes by maximizing the posterior probability that it represents the note sequence. Prior musical input from a given user as well as explicit information about the musical style of the input may be used to improve the accuracy of the transcription.

Abstract: An example computer of an information processing apparatus that reproduces music composed of one or more tracks is caused to function as: a reproduction section configured to reproduce the music; a meter change section configured to change the meter for reproduction of the music, while the reproduction section is reproducing the music; and a determination section configured to, based on the meter that has been changed, repeatedly determine whether or not to cause the reproduction section to reproduce the next beat supposed to be reproduced in a bar of the music that is currently being reproduced. The reproduction section reproduces the music, based on the result of the determination by the determination section.

Abstract: A guitar delay engine such as a multi-tap delay pedal or other rhythm engine such as a vocal multi-tap delay pedal, a drum machine, or any other device that requires setting a rhythmic pattern (i.e. level and timing information) for operation is provided. In a guitar delay device, the guitarist can hold down a foot pedal, play a rhythmic pattern on their guitar, and then release the foot pedal and have the rhythmic pattern just played emulated in the delay pattern on the device.

Abstract: An apparatus for enhancing audio comprising a first interface and a harmonizing module is disclosed. The first interface receive a first audio segment from a first source. The harmonizing module is coupled to the first interface. The harmonizing module is configured to identify at least one musical property of the first audio segment; calculate a subset of notes that are harmonious with the first audio segment based on the at least one musical property; and select from the subset of notes to generate an audio track to be played substantially synchronously with the first audio segment. A second interface may also be provided to receive a second audio segment from a second source. In this case, the harmonizing module may be configured to generate the audio track by transforming one or more notes of the second audio segment. A method is also provided.

Abstract: An apparatus that allows a musical piece to be recomposed by reflecting, for example, the mood, preference, and ambient environment of a listening user in the musical piece in real time. The apparatus includes a rhythm master unit and a rhythm slave unit. The rhythm master unit generates synchronization signals containing a signal having a period corresponding to a measure of a musical piece and a signal having a period corresponding to a beat of the musical piece and also generates musical-piece recomposition information in synchronization with the synchronization signals. The rhythm slave unit recomposes musical-piece data of input music content in accordance with the synchronization signals and the musical-piece recomposition information, generates output musical-piece data, and outputs the musical-piece data to the rhythm slave unit.

Abstract: The present invention relates to a percussion assembly comprising a multitude of percussion instruments, means for playing said percussion instruments and input means for inputting a tone pitch selection for the purpose of producing a tone pitch selection signal. The percussion assembly further comprises sensor means for producing a synchronization signal when at least one of said percussion instruments is being played. The percussion assembly furthermore comprises control means for receiving the tone pitch selection signal and the synchronization signal and for producing an audio signal dependent on the tone pitch selection signal synchronously with the synchronization signal. The invention further relates to drumsticks and to input means for use with a percussion assembly as described in the foregoing.

Abstract: Systems and methods of evolving music tracks are disclosed. One example method providing a plurality of Artificial Neural Networks (ANNs). Each of the ANNs uses a time signature input. The method also includes producing a rhythm from each of the plurality of ANNs. The method also includes evolving a next generation of ANNs based upon a user selection of one of the plurality of rhythms and upon the previous generation of ANNs. An example system includes a plurality of Compositional Pattern Producing Networks (CPPNs). Each of the CPPNs uses a time signature input to produce a rhythm. The system also includes logic configured to receive a selection of one or more of the CPPN, and logic configured to generate at least one evolved CPPN based upon the selection.

Abstract: A synthesizer 10 is configured such that when a PC 30 is connected thereto, the synthesizer 10 accepts selection of a tone used for sound generation from among a tone included in an internal tone generation unit 16 and a tone included in a tone generation module 312 provided by the external PC 30, and causes the PC 30 to enable the function of the tone generation module 312, downloads an edit operation accepting program corresponding to the tone generation module 312 from a UI control program memory 315 of the PC 30, and executes the downloaded edit operation accepting program to thereby realize a function of editing data of the tone included in the tone generation module 312, the data being stored in the PC 30, when the tone included in the tone generation module 312 of the PC 30 is selected.

Abstract: A method for providing real-time musical interaction among a plurality of players connected via a network includes the steps of receiving input from a local player representing a musical performance, generating audio output responsive to the received input, receiving second music performance data from a remote player representing a musical performance by the remote player, creating emulation data representing the remote musical performance, and using the emulation data to generate a local approximation of the remote musical performance.

Abstract: A user is asked to perform tapping at beat positions by using a tapping detection section while listening to the beginning of a waveform from which beats are to be detected. When a fluctuation calculation section determines that tapping fluctuation falls in a predetermined range, a beat interval close in number to the tempo of the tapping is selected from among beat-interval candidates detected by a tempo-candidate detection section, and a tapping position where tapping becomes stable is determined to be the starting beat position. Tapping by the user for just some beats allows beats to be detected in the entire musical piece more correctly.

Abstract: An audio management application includes a recombiner and aggregation rules to manipulate and recombine segments of a musical piece such that the resulting finished composition includes parts (segments) from the decomposed piece, typically a song, adjustable for length by selectively replicating particular parts and combining with other parts such that the finished composition provides a similar audio experience in the predetermined duration. The architecture defines the parts with part variations of independent length, identified as performing a function of starting, middle, (looping) or ending parts. Each of the parts provides a musical segment that is integratable with other parts in a seamless manner that avoids audible artifacts (e.g. “pops” and “crackles”) common with conventional mechanical switching and mixing.

Abstract: An encoded rhythmic pattern has several groups of velocity values, wherein the velocity values are sorted, such that the groups are included in sequence in an encoded rhythmic pattern. Now, the velocity values concentrated at the beginning of the encoded rhythmic pattern have a higher importance for characterizing the rhythmic gist of a piece of music than velocity values included in additional groups of velocity values. By using such an encoded rhythmic pattern, an efficient database access can be performed.

Abstract: An encoded rhythmic pattern has several groups of velocity values, wherein the velocity values are sorted, such that the groups are included in sequence in an encoded rhythmic pattern. Now, the velocity values concentrated at the beginning of the encoded rhythmic pattern have a higher importance for characterizing the rhythmic gist of a piece of music than velocity values included in additional groups of velocity values. By using such an encoded rhythmic pattern, an efficient database access can be performed.

Abstract: An apparatus for analyzing an audio signal with regard to rhythm information of the audio signal by using an autocorrelation function comprises a filter bank for separating the audio signal into at least two sub-band signals. The sub-band signals are examined with regard to periodicities by an autocorrelation function, to obtain rhythm raw-information for the at least two sub-band signals. To reduce or eliminate the ambiguities of the autocorrelation function for periodical signals, the rhythm raw-information is postprocessed to obtain post-processed rhythm raw-information for the sub-band signal. The rhythm information of the audio signal is established based on the postprocessed rhythm raw-information.

Abstract: A method for determining rhythm units (beats per minute or BPM) in (digital) audio data forming a musical piece. The audio data is split among a plurality of determination paths wherein it is subdivided into predetermined frequency bands. The data is analyzed for transients in order to determine attack events. In addition, the time intervals between two successive attack events are measured. In this case, the time intervals are averaged and defined as the frequency-band-specific rhythm unit (BPM) of the audio data in the respective determination path. Thus, the rhythm unit which exhibits the highest beat number (BPM number) is selected from the frequency-band-specific rhythm units (BPM) of the determination paths.

Abstract: A musical data performance system comprises a first changing pattern generator that generates a first changing pattern by combining a plurality of note lengths and an effect giving device that gives an effect to a tone signal in accordance with the generated first changing pattern.

Abstract: An apparatus for analyzing an audio signal with regard to rhythm information of the audio signal by using an autocorrelation function comprises a filter bank for separating the audio signal into at least two sub-band signals. The sub-band signals are examined with regard to periodicities by an autocorrelation function, to obtain rhythm raw-information for the at least two sub-band signals. To reduce or eliminate the ambiguities of the autocorrelation function for periodical signals, the rhythm raw-information is postprocessed to obtain post-processed rhythm raw-information for the sub-band signal. The rhythm information of the audio signal is established based on the postprocessed rhythm raw-information.

Abstract: A method for determining rhythm units (beats per minute or BPM) in (digital) audio data forming a musical piece. The audio data is split among a plurality of determination paths wherein it is subdivided into predetermined frequency bands. The data is analyzed for transients in order to determine attack events. In addition, the time intervals between two successive attack events are measured. In this case, the time intervals are averaged and defined as the frequency-band-specific rhythm unit (BPM) of the audio data in the respective determination path. Thus, the rhythm unit which exhibits the highest beat number (BPM number) is selected from the frequency-band-specific rhythm units (BPM) of the determination paths.

Abstract: In the sound signal adding apparatus in which there is a limitation on the number of reproducible sound sources, a remaining reproduction time determining section and a sound data attenuation controlling section are provided. The remaining reproduction time determining section checks, when sound data is to be added and reproduced, the remaining reproduction time of the sound data current being reproduced and detects a sound data having least reproduction time remaining. While the sound data attenuation controlling section reduces the output level of the sound signal corresponding to the sound data detected by the remaining reproduction time determining section.

Abstract: The invention relates to a method of extracting a representation of its rhythmic structure, from a given signal. The representation is designed to yield a similarity relation between item titles.

Abstract: A method for automatically creating dance patterns using an audio signal of music, comprising: extracting power feature of an audio signal of each processing window by covering the audio signal with the processing window for analyzing the audio signal at regular intervals, and extracting the processing windows indicating a part having strong-beat power feature as beating window candidates; determining beating windows corresponding to the points where beating should be conducted according to predetermined dance pattern creating option, out of the beating window candidates; and assigning predetermined unique beating codes to the determined beating windows in order of dance patterns based on the dance pattern creating option, and creating beating data of the dance patterns using the beating codes and time information indicating a time interval between beating windows.

Abstract: An apparatus has an insert pattern play instruction unit (54) for selecting a desired insert pattern and instructing to play the selected pattern, and a bar count display unit (57) for displaying the number of bars of the selected insert pattern upon playing the selected insert pattern. Since the number of bars of a desired insert pattern is displayed at the beginning of the play of the insert pattern, even when the player does not remember the numbers of bars of insert patterns, which are different in units of rhythm styles, he or she can recognize the end timing of that insert pattern, and can easily enjoy a manual play in accordance with that pattern.

Abstract: A system for searching music, based upon music content that may be described by a plurality of predetermined feature vectors is provided. The system includes a user interface that can receive a plurality of user requests for searching music, wherein the user requests define a set of search parameters. A user enters search parameters into the user interface that allows a user to vary the plural levels of the plural feature vectors. The system further includes a user interface engine that receives the user requests for searching music based upon user chosen feature vector levels, wherein the user interface includes a parser for parsing the user requests. The system also includes an inferential engine that performs a search for music by comparing plural feature vectors.

Abstract: A system and method are disclosed for automatically generating music on the basis of an initial sequence of input notes, and in particular to such a system and method utilizing a recursive artificial neural network (RANN) architecture. The aforementioned system includes a score interpreter (2) interpreting an initial input sequence, a rhythm production RANN (4) for generating a subsequent note duration, a note generation RANN (6) for generating a subsequent note, and feedback means for feeding the pitch and duration of the subsequent note back to the rhythm generation (4) and note generation (6) RANNs, the subsequent note thereby becoming the current note for a following iteration.

Abstract: Sound generation control and instruction operation evaluation is performed by sound group selection and a sound generation instruction, with a mimic guitar having selection buttons for selecting one of a plurality of sound groups bearing a series of sounds, and a picking blade for instructing the generation of a sound. The rhythm-matching game can be enjoyed relatively easily in a manner closer to a realistic state of playing an instrument.

Abstract: A music apparatus is constructed for selecting style data of a music piece by designating a style name of the music piece among a plurality of music pieces, which are sorted by genres. In the music apparatus, a style selection table is provided for recording selection codes assigned to the style names of the music pieces in a sorted manner by genres, such that different selection numbers may be assigned to the same style name when the music piece labeled thereby is sorted into more than one genre. A conversion table is provided for recording a correspondence between each selection code and each style name. A data memory is provided for storing each style data of each music piece in correspondence to the style name of each music piece. A monitor presents the selection codes together with the style names according to the style selection table in the sorted manner by the genres. A control is operated to designate a selection code from a desired genre presented on the monitor.

Abstract: In an automatic accompanying apparatus and an automatic accompanying method, the respective part structures of a plurality of basic variation patterns used as a basic accompanying pattern of rhythm are arbitrarily set by a music player. When the music player selects one basic variation pattern from a plurality of basic variation patterns to which the part structures are set in such a manner, the part structure is automatically set in such a manner that part structures of an intro-pattern, an ending pattern, and also a fill-in pattern, which are prepared for this rhythm, are made equal to the part structure of the selected basic variation pattern. The automatic accompaniment is carried out by employing the selected basic variation pattern, and the intro-pattern, ending pattern, and fill-in pattern, which own the same part structures as that of this basic variation pattern. As a result, the automatic accompaniment can be carried out while being matched with a motif of a user through the entire music.

Abstract: A rhythmic tone generator includes a casing that houses a rhythm signal generating circuit, a battery and a tone generating device, and that is positioned and held on the concha by an attaching device, so that the rhythmic tone generator is attached to the ear without being inserted into the ear hole, and operates to generate rhythmic tones right in the vicinity of the ear hole. On the rear surface of the casing are disposed a display device connected to the rhythmic tone generating circuit and operable to display a parameter representing the speed of the rhythm signal, and a push-button switch that may be operated with a hand while the tone generator is being attached to the ear.

Abstract: A system, and related method, for creating music in real time includes an input device and a real-time music generator. The input device is used by a user to provide rhythm-related signals and pitch-related signals to the real-time music generator. The real time music generator receives the rhythm-related and pitch-related signals and creates or composes in real time music that includes pitches based on the pitch-related signals and rhythmic activity based on the rhythm-related signals. The input device can provide pitch related and rhythm-related signals that are representative of position, velocity, or acceleration. The real-time music generator can derive position, velocity, or acceleration from the pitch-related and rhythm-related signals and compose in real time music comprising pitches and rhythm activity based on the derived information.

Abstract: To present a holonic rhythm generator capable of generating rhythm following free changes by transmitting the intent of tempo change from the action of man to rhythm generator in real time, or, to the contrary, guiding the action rhythm of man gradually by the rhythm generator. To achieve the object, the device has a rhythm generator having such constitution described by a nonlinear vibration equation which is a van der Pol's formula a constant portion of which is replaced by a cubic expression, and a fixed rhythm generator and action rhythm detector for generating an input signal of the rhythm generator, in which a specific relation is given between the fixed rhythm generator and action rhythm detector.

Abstract: When a switching operation from a normal pattern to a special pattern is instructed while an automatic accompaniment operation is being executed using normal pattern data, the pattern to be read out is switched from the normal pattern to the special pattern in accordance with the instruction. In this case, when it is instructed to switch the pattern within the instructed bar, only a rhythm part of a plurality of parts is switched from the normal pattern to the special pattern. When it is instructed to switch the pattern at the beginning of the next bar, other parts in addition to the rhythm part are switched from the normal patterns to the special patterns.

Abstract: An electronic musical instrument with an automatic performance function includes manual performance device, an automatic performance device and a control. The manual performance device, having a plurality of performance manipulators to be performed by a player, generates a manual performance musical tone having a tone color in response to the player's performing. The automatic performance device automatically generates automatic performance musical tones of a plurality of parts respectively corresponding to a plurality of tone colors. The control, in response to generation of the manual performance musical tone.

Abstract: An electronic rhythm instrument having two or more rhythm switches which correspond to rhythmical sounds, and which generates rhythmical sounds corresponding to the rhythm switch operated. In the electronic rhythm instrument, one of the rhythmical sounds can be assigned commonly to a plurality of the rhythm switches, and further, a tone pitch and/or a tone volume can be assigned to each rhythm switch to which one of the rhythmical sounds is assigned commonly when a primary mode is selected. After the assignment, when a secondary mode is selected and one of the rhythm switches is operated, the preassigned rhythmical sound having the tone pitch and/or the tone volume assigned to the operated rhythm switch can be generated. The present invention can assign a tone-pitch scale and/or a tone-volume scale to a number of rhythm switches. When the tone-pitch scale is assigned to the rhythm switches, a melody can be produced according to the tone-pitch scale.

Abstract: A rhythm pattern generating apparatus is provided having a layered neural network to perform learning with feedback to generate an output pattern signal indicative of a musical sound pattern. The output pattern signal is generated by the layered neural network with feedback in response to a performance operation of a player. The layered neural network generates the output pattern signal indicative of the musical sound pattern based on both an input pattern signal and a weight signal. The output pattern signal is fed back by the feedback circuit to the layered neural network to perform the learning process. A drum pad can be used to provide an input to the rhythm pattern generating apparatus or, specifically, to gate an input pattern selector for selecting input pattern signals. The layered neural network with the feedback can perform the learning process using a back propagation method.

Abstract: A rhythm play control device for an electronic musical instrument stores the number of operations of a single operator, and includes a memory device and a central processing unit which responds thereto to perform a change of play mode of the instrument.

Abstract: A plurality of pad operating means for manual operation are provided on a keyboard panel of an electronic keyboard musical instrument. When an operator operates the pad operating means using the keyboard during melody play, an operation signal is supplied to a CPU, and a rhythm sound corresponding to the operated pad is generated under control of the CPU. An automatic sound signal generator is provided for generating and outputting sound signals according to a designated rhythm, and selectively stops such sound signal generation. A sounding system is provided for sounding the signals received thereby.