v.morish’09: A Morphing-Based Singing Design Interface for Vocal Melodies

Morise, Masanori; Onishi, Masato; Kawahara, Hideki; Katayose, Haruhiro

doi:10.1007/978-3-642-04052-8_18

Cited by 20 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods include concatena tive synthesis methods and hidden Markov model (HMM) synthesis methods. Other examples include a system for analyzing, process ing, and synthesizing scat singing [17], singing morphing that blends different singing styles [18][19][20], and singing synthesis that imitates the user's singing performance [21,22].…”

Section: Singing Synthesismentioning

confidence: 99%

Singing information processing

Goto

2014

2014 12th International Conference on Signal Processing (ICSP)

View full text Add to dashboard Cite

This paper introduces singing information processing, which is de fined as music information processing for singing voices. As many people listen to music with a focus on singing, singing is one of the most important elements of music. Singing information process ing attracts attention not only from a scientific point of view but also from the standpoint of commercial applications, such as singing syn thesis, automatic singing pitch correction, query-by-humming, and singing skill evaluation for karaoke. The concept of singing infor mation processing is broad and still emerging.Index Terms-Singing information processing, music informa ti on research

show abstract

Section: Singing Synthesismentioning

confidence: 99%

Singing information processing

Goto

2014

2014 12th International Conference on Signal Processing (ICSP)

View full text Add to dashboard Cite

show abstract

“…Which F0 estimator to use depends on the purpose of study. For real-time speech analysis/synthesis applications [14,2], DIO [15] and its improved version [16] have been proposed. For high-quality speech analysis/synthesis systems, NDF [17] used in STRAIGHT [18] and XSX used in TANDEM-STRAIGHT [19,20] are preferred.…”

Section: Related Work On F0 Estimationmentioning

confidence: 99%

Harvest: A High-Performance Fundamental Frequency Estimator from Speech Signals

Morise

2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

A fundamental frequency (F0) estimator named Harvest is described. The unique points of Harvest are that it can obtain a reliable F0 contour and reduce the error that the voiced section is wrongly identified as the unvoiced section. It consists of two steps: estimation of F0 candidates and generation of a reliable F0 contour on the basis of these candidates. In the first step, the algorithm uses fundamental component extraction by many band-pass filters with different center frequencies and obtains the basic F0 candidates from filtered signals. After that, basic F0 candidates are refined and scored by using the instantaneous frequency, and then several F0 candidates in each frame are estimated. Since the frame-by-frame processing based on the fundamental component extraction is not robust against temporally local noise, a connection algorithm using neighboring F0s is used in the second step. The connection takes advantage of the fact that the F0 contour does not precipitously change in a short interval. We carried out an evaluation using two speech databases with electroglottograph (EGG) signals to compare Harvest with several state-of-the-art algorithms. Results showed that Harvest achieved the best performance of all algorithms.

show abstract

“…Real-time singing morphing [11] has the same problem. TANDEM-STRAIGHT [12], [13] is supposed to be a simplified version that outputs almost all the same parameters as STRAIGHT.…”

Section: Introductionmentioning

confidence: 99%

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications

Morise

Yokomori

Ozawa

2016

IEICE Trans. Inf. & Syst.

Self Cite

1,000

597

View full text Add to dashboard Cite

SUMMARYA vocoder-based speech synthesis system, named WORLD, was developed in an effort to improve the sound quality of realtime applications using speech. Speech analysis, manipulation, and synthesis on the basis of vocoders are used in various kinds of speech research. Although several high-quality speech synthesis systems have been developed, real-time processing has been difficult with them because of their high computational costs. This new speech synthesis system has not only sound quality but also quick processing. It consists of three analysis algorithms and one synthesis algorithm proposed in our previous research. The effectiveness of the system was evaluated by comparing its output with against natural speech including consonants. Its processing speed was also compared with those of conventional systems. The results showed that WORLD was superior to the other systems in terms of both sound quality and processing speed. In particular, it was over ten times faster than the conventional systems, and the real time factor (RTF) indicated that it was fast enough for real-time processing.

show abstract

v.morish’09: A Morphing-Based Singing Design Interface for Vocal Melodies

Cited by 20 publications

References 5 publications

Singing information processing

Singing information processing

Harvest: A High-Performance Fundamental Frequency Estimator from Speech Signals

WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications

Contact Info

Product

Resources

About