Yamaha Corporation

Pompeu Fabra University

Other

Jordi Bonada

Merlijn Blaauw

Keijiro Saino

Yasuo Yoshioka

Takuya Fujishima

Ryunosuke Daido

Xavier Serra

Yuji Hisaminato

Hideki Kemmochi

Alex Loscos

Yasuyuki Umeyama

Kazunobu Kondo

Sebastian Streich

Maarten De Boer

Jordi Janer

Ricard Marxer

Hiraku Kayama

Takahiro Kawashima

Samuel Roig

Pedro Cano

Mark Schiementz

Hideki Kenmochi

Yu Takahashi

Makoto Tachibana

Bee Suan Ong

Michael Wilson

Oscar Mayor

Fokke De Jong

Francisco Garcia

Takuya Yamaha Corporation Fujishima

An information processing system includes at least one memory storing a program and at least one processor. The at least one processor implements the program to input a piece of sound source data obtained by encoding a first identification data representative of a sound source, a piece of style data obtained by encoding a second identification data representative of a performance style, and synthesis data representative of sounding conditions into a synthesis model generated by machine learning, and to generate, using the synthesis model, feature data representative of acoustic features of a target sound of the sound source to be generated in the performance style and according to the sounding conditions, and to generate an audio signal corresponding to the target sound using the generated feature data.

Information processing method and information processing system for sound synthesis utilizing identification data associated with sound source and performance styles

A sound processing method obtains note data representative of a note; obtains an audio signal to be processed; specifies, in accordance with the note, an expression sample representative of a sound expression to be imparted to the note and an expression period, of the audio signal, to which the sound expression is to be imparted to the note; and specifies, in accordance with the expression sample and the expression period, a processing parameter relating to an expression imparting processing for imparting the sound expression to a portion corresponding to the expression period in the audio signal. The method then generates a processed audio signal by performing the expression imparting processing in accordance with the expression sample, the expression period, and the processing parameter to the audio signal.

Sound processing method, sound processing apparatus, and recording medium

A computer-implemented sound signal generation method includes: obtaining a first sound source spectrum of a sound signal to be generated; obtaining a first spectral envelope of the sound signal; and estimating fragment data representative of samples of the sound signal based on the obtained first sound source spectrum and the obtained first spectral envelope.

Sound signal generation method, generative model training method, sound signal generation system, and recording medium

A voice synthesis method according to an embodiment includes altering a series of synthesis spectra in a partial period of a synthesis voice based on a series of amplitude spectrum envelope contours of a voice expression to obtain a series of altered spectra to which the voice expression has been imparted, and synthesizing a series of voice samples to which the voice expression has been imparted, based on the series of altered spectra.

Voice synthesis method, voice synthesis device, and storage medium

A voice synthesis method includes: sequentially acquiring voice units comprising at least one of diphone or a triphone in accordance with synthesis information for synthesizing voices; generating statistical spectral envelopes using a statistical model built by machine learning in accordance with the synthesis information for synthesizing the voices; and concatenating the sequentially acquired voice units and modifying a frequency spectral envelope of each voice unit in accordance with the generated statistical spectral envelope, thereby synthesizing a voice signal based on the concatenated voice units having the modified frequency spectra.

Voice synthesis apparatus and voice synthesis method utilizing diphones or triphones and machine learning

A voice synthesis method for generating a voice signal through connection of a phonetic piece extracted from a reference voice, includes selecting, by a piece selection unit, the phonetic piece sequentially; setting, by a pitch setting unit, a pitch transition in which a fluctuation of an observed pitch of the phonetic piece is reflected based on a degree corresponding to a difference value between a reference pitch being a reference of sound generation of the reference voice and the observed pitch of the phonetic piece selected by the piece selection unit; and generating, by a voice synthesis unit, the voice signal by adjusting a pitch of the phonetic piece selected by the piece selection unit based on the pitch transition generated by the pitch setting unit.

Voice synthesis method, voice synthesis device, medium for storing voice synthesis program

A processing unit of a voice processing apparatus first generates a target voice signal in a time domain by adjusting a fundamental frequency of a target voice signal to a fundamental frequency of an initial voice signal, so as to generate a spectrum of the target voice signal after pitch is adjusted. Second, the processing unit reallocates, along a frequency axis, the spectrum of the target voice characteristics by having the spectrum correspond to each of the fundamental frequencies of the initial voice signal. The processing unit then generates a converted spectrum by adjusting component values of the spectrum of the target voice characteristics, which spectrum has been reallocated, so as to correspond to the component values of the spectrum of the initial voice signal, and by adapting the component values of the spectrum of the initial voice signal to specific frequency bands of the spectrum of the target voice characteristics, with each specific frequency band including one of the harmonic frequencies corresponding to the fundamental frequency of the initial voice signal.

Voice processing method and apparatus, and recording medium therefor

In a voice processing apparatus, a processor is configured to adjust, a fundamental frequency of a first voice signal corresponding to a voice having target voice characteristics to a fundamental frequency of a second voice signal corresponding to a voice having initial voice characteristics different from the target voice characteristics. The processor is further configured to sequentially generate a processed spectrum based on a spectrum of the first voice signal and a spectrum of the second voice signal by: dividing the spectrum of the first voice signal into a plurality of harmonic band components after the fundamental frequency of the first voice signal has been adjusted; allocating each harmonic band component of the first voice signal to each harmonic frequency associated with the fundamental frequency of the second voice signal; and adjusting an envelope and phase of each harmonic band component according to the spectrum of the second voice signal.

Voice processing apparatus

Candidate frequencies per unit segment of an audio signal are identified. First processing section identifies an estimated train that is a time series of candidate frequencies, each selected for a different one of the segments, arranged over a plurality of the unit segments and that has a high likelihood of corresponding to a time series of fundamental frequencies of a target component. Second processing section identifies a state train of states, each indicative of one of sound-generating and non-sound-generating states of the target component in a different one of the segments, arranged over the unit segments. Frequency information which designates, as a fundamental frequency of the target component, a candidate frequency corresponding to the unit segment in the estimated train is generated for each unit segment corresponding to the sound-generating state. Frequency information indicative of no sound generation is generated for each unit segment corresponding to the non-sound-generating state.

Technique for estimating particular audio component

A coefficient train processing section, which sequentially generates per unit segment a processing coefficient train for suppressing a target component of an audio signal, includes a basic coefficient train generation section and coefficient train processing section. The basic coefficient train generation section generates a basic coefficient train where basic coefficient values corresponding to frequencies within a particular frequency band range are each set at a suppression value that suppresses the audio signal while coefficient values corresponding to frequencies outside the particular frequency band range are each set at a pass value that maintains the audio signal. The coefficient train processing section generates the processing coefficient train, per unit segment, by changing, to the pass value, each of the coefficient values corresponding to frequencies other than the target component among the coefficient values corresponding to the frequencies within the particular frequency band range.

Technique for suppressing particular audio component

Signal processing section of a terminal converts acquired audio signals of a plurality of channels into frequency spectra set, calculates sound image positions corresponding to individual frequency components, and displays, on a display screen, the calculated sound image positions results by use of a coordinate system having coordinate axes of the frequency components and sound image positions. User-designated partial region of the coordinate system is set as a designated region and an amplitude-level adjusting amount is set for the designated region, so that the signal processing section adjusts amplitude levels of frequency components included in the frequency spectra and in the designated region, converts the adjusted frequency components into audio signals and outputs the converted audio signals.

Graphical audio signal control

In a voice synthesis apparatus, a phoneme piece interpolator acquires first phoneme piece data corresponding to a first value of sound characteristic, and second phoneme piece data corresponding to a second value of the sound characteristic. The first and second phoneme piece data indicate a spectrum of each frame of a phoneme piece. The phoneme piece interpolator interpolates between each frame of the first phoneme piece data and each frame of the second phoneme piece data so as to create phoneme piece data of the phoneme piece corresponding to a target value of the sound characteristic which is different from either of the first and second values of the sound characteristic. A voice synthesizer generates a voice signal having the target value of the sound characteristic based on the created phoneme piece data.

Voice synthesis apparatus

Variation over time in fundamental frequency in singing voices is separated into a melody-dependent component and a phoneme-dependent component, modeled for each of the components and stored into a singing synthesizing database. In execution of singing synthesis, a pitch curve indicative of variation over time in fundamental frequency of the melody is synthesized in accordance with an arrangement of notes represented by a singing synthesizing score and the melody-dependent component, and the pitch curve is corrected, for each of pitch curve sections corresponding to phonemes constituting lyrics, using a phoneme-dependent component model corresponding to the phoneme. Such arrangements can accurately model a singing expression, unique to a singing person and appearing in a melody singing style of the person, while taking into account phoneme-dependent pitch variation, and thereby permits synthesis of singing voices that sound more natural.

Apparatus and method for creating singing synthesizing database, and pitch curve generation apparatus and method

Waveform data representative of singing voices of a singing music piece are analyzed to generate melody component data representative of variation over time in fundamental frequency component presumed to represent a melody in the singing voices. Then, through machine learning that uses score data representative of a musical score of the singing music piece and the melody component data, a melody component model, representative of a variation component presumed to represent the melody among the variation over time in fundamental frequency component, is generated for each combination of notes. Parameters defining the melody component models and note identifiers indicative of the combinations of notes whose variation over time in fundamental frequency component are represented by the melody component models are stored into a pitch curve generating database in association with each other.

In an audio signal processing apparatus, a generation section generates an audio signal representing a voice. A distribution section distributes the audio signal generated by the generation section to a first channel and a second channel, respectively. A delay section delays the audio signal of the first channel relative to the audio signal of the second channel for creating a phase difference between the audio signal of the first channel and the audio signal of the second channel such that the created phase difference has a duration corresponding to either an added value of a first duration which is approximately one half of a period of the audio signal generated by the generation section and a second duration which is set shorter than the first duration, or a difference value of the first duration and the second duration. An addition section adds the audio signal of the first channel and the audio signal of the second channel with one another, between which the phase difference is created by the delay section, and outputs the added audio signal which represents natural voice with various characteristics.

Growing community of inventors

Barcelona, Spain

Jordi Bonada