Development of an F0 control model based on F0 dynamic characteristics for singing-voice synthesis

Saitou, Takeshi; Unoki, Masashi; Akagi, Masato

doi:10.1016/j.specom.2005.01.010

Cited by 68 publications

(56 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Now F 0 quickly decreased and then steadily increased. Such findings are in good qualitative agreement with experimental data on F 0 [1]. It can be observed in Fig.…”

Section: Resultssupporting

confidence: 91%

“…The time-independent equilibrium network is characterized by Ogden's hyperelastic model which provides a nonlinear correlation between stretch and stress. For uniaxial loading conditions with applied stretch λ u the corresponding Cauchy stress σ is given as: (1) where σ A is the Cauchy stress and μ A is the initial shear modulus of the equilibrium network (A), α is the corresponding dimensionless constant describing the nonlinearity of the elastic response, and λ u is the applied stretch.…”

Section: A Constitutive Characterization Of Vocal Fold Tissuementioning

confidence: 99%

“…Extensive efforts have been made in signal processing to describe and predict the temporal contour of F 0 changes during speech or singing, e.g., Saitou et al [1] proposed a F 0 control model and showed several types of F 0 fluctuations in singing voice including pronounced over and undershoots at pitch changes; Kutik et al [2] reported a tendency for the fundamental frequency to drop towards the end of a declarative sentence, which is termed F 0 declination; Möbius [3] reported over and undershoots associated with syllables. However, few studies have been conducted to explain these local fluctuations and global changes of F 0 from a predictive point of view.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictions of Fundamental Frequency Changes During Phonation Based on a Biomechanical Model of the Vocal Fold Lamina Propria

et al. 2009

View full text Add to dashboard Cite

This study examines the local and global changes of fundamental frequency (F 0 ) during phonation and proposes a biomechanical model of predictions of F 0 contours based on the mechanics of vibration of vocal fold lamina propria. The biomechanical model integrates the constitutive description of the tissue mechanical response with a structural model of beam vibration. The constitutive model accounts for the nonlinear and time dependent response of the vocal fold cover and the vocal ligament. The structural model of the vocal fold lamina propria is based on a composite beam model with axial stress. Results show that local fluctuations such as F 0 overshoots and undershoots can be characterized by the biomechanical model and might be related to the processes of stress relaxation of vocal fold tissues during length changes. The global changes of F 0 declination in declarative sentence production can also be characterized by the model. Such F 0 declination is partially attributed to the peak stress decay associated with stress relaxation of the vocal fold lamina propria and partially to neuromuscular control of the vocal fold length.

show abstract

“…Now F 0 quickly decreased and then steadily increased. Such findings are in good qualitative agreement with experimental data on F 0 [1]. It can be observed in Fig.…”

Section: Resultssupporting

confidence: 91%

Section: A Constitutive Characterization Of Vocal Fold Tissuementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predictions of Fundamental Frequency Changes During Phonation Based on a Biomechanical Model of the Vocal Fold Lamina Propria

et al. 2009

View full text Add to dashboard Cite

show abstract

“…As a system to synthesize a chorus voice, a vocal conversion system, which has been developed by Saitou et al [8] to synthesize a singing voice given a speaking voice and a musical score, was utilized. This synthesizer is based on the speech manipulation system widely known as STRAIGHT [9], and controls four F 0 fluctuations: overshoot, vibrato, preparation, and fine fluctuation.…”

Section: Synthesis Of Chorus Voicementioning

confidence: 99%

Synchronization analysis of choir singing

Tokuda

Kuwahara

2012

NOLTA

View full text Add to dashboard Cite

Synchronization plays an essential role in choir singing. Fundamental frequencies of the singing voices should satisfy a rational frequency relationship to produce harmony. The present study attempts to clarify basic properties of synchronization that may influence the chorus quality. As the key features of synchronization, frequency mismatch and timing mismatch were considered. Combining the synthesis technique of choir singing, which can precisely control the detailed frequency structure of the singing voice, with psychoacoustic experiment, criterions were obtained to roughly discriminate good choruses from bad ones. To examine the reliability of the psychoacoustic experiment, acoustic analysis of the singing voices in real chorus was further carried out.

show abstract

“…Most related work [4,5] investigate the differences between singing and speech. Some studies develop methods for singing voice synthesis [6,7], and some discuss how to convert speech into singing [8], according to the specified melody. This work investigates two SNID systems trained using spoken data.…”

Section: Introductionmentioning

confidence: 99%

Automatic Singer Identification Based on Speech-Derived Models

Tsai¹,

Lee²

2012

IJFCC

View full text Add to dashboard Cite

Abstract-Automatic singer identification (SNID) aims to determine who among a set of singers perform a given music recording. So far, most existing SNID methods follow a framework stemming from speaker identification (SPID) research, which models each person's characteristics using his/her voice data. This framework, however, is impractical in many SNID applications, because acquiring solo a cappella from each singer is usually not as feasible as collecting spoken data from each speaker in SPID applications. In view of the easy availability of spoken data, this work investigates the possibility of modeling singers' voices using spoken data instead of singing data. However, our experiment found it difficult to replace singing data fully by using spoken data in singer voice modeling, due to the significant difference between singing and speaking for most people. Thus, we propose an alternative solution based on the use of few available singing data. The idea is to modify speech-derived voice models using MAP adaptation on few singing data, so that the adapted voice models can cover performers' singing characteristics. Our experiments found that most of the singing clips can be correctly identified using the adapted voice models.Index Terms-Model adaptation, singer identification, speaker identification.

show abstract

Development of an F0 control model based on F0 dynamic characteristics for singing-voice synthesis

Cited by 68 publications

References 12 publications

Predictions of Fundamental Frequency Changes During Phonation Based on a Biomechanical Model of the Vocal Fold Lamina Propria

Predictions of Fundamental Frequency Changes During Phonation Based on a Biomechanical Model of the Vocal Fold Lamina Propria

Synchronization analysis of choir singing

Automatic Singer Identification Based on Speech-Derived Models

Contact Info

Product

Resources

About