Macon, M., Link, J., Oliverio, L., Clements, J., George, E. A singing voice synthesis system based on sinusoidal modeling. In Proc. ICASSP 97, Munich, Germany, Apr. 1997. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
An Audio Front End for Query-by-Humming Systems - Haus, Pollastri (2001) (5 citations) (Correct)
....research field, especially in the framework of voice analysis re synthesis. Typical examples are the voice morphing system by Loscos et al. 10] the structured audio approach to singing analysis score driven by Kim [6] and the synthesis of voice based on sinusoidal modeling by Macon et al. [11]. 3. BACKGROUND Despite its monophonic nature, singing has proved to be difficult to analyze [21] The time varying spectral characteristics of voice are similar during speech and singing. In both cases, we can divide the generated sounds in voiced and unvoiced 1 . In order to have an ....
Macon, M., Link, J., Oliverio, L., Clements, J., George, E. A singing voice synthesis system based on sinusoidal modeling. In Proc. ICASSP 97, Munich, Germany, Apr. 1997.
VowSynth: A Synthesizer of Vowel Sounds based on Additive Synthesis - Guerra (Correct)
....them with sinusoids. These partials are then subtracted from the original sound and the remaining residual can be approximated as a stochastic signal, for example, filtered white noise. Two recent methods which also use spectral methods are the software designed by K. Lomax [3] and LYRICOS [4]. In our first approximation to a voice synthesizer some restrictions have been made. On one hand, only vowels will be synthesized; consonants present problems that go beyond the current work. Because of this restriction the synthesizer will not use the residual part of the sound obtained by SMS, ....
M. Macon and others. "A Singing Voice Synthesis System based on Sinusoidal Modeling". Proc. ICASSP, 1997. [available at http://www.cse.ogi.edu/CSLU/publications/ abstracts/icassp97/macon.html]
Concatenation-based MIDI-to-Singing Voice Synthesis - Macon, Jensen-Link, al. (1997) (4 citations) Self-citation (Macon Jensen-link Oliverio Clements) (Correct)
....to analysis and resynthesis of selected voice sounds like sustained vowels or consonant vowel syllables, including formant synthesis [1] wavetables [2] and FM synthesis [3, 4] Controllable articulatory models such as the SPASM system [5, 6, 7] have also been applied in this area. In recent work [8, 9] the use of concatenationbased synthesis of voice has begun to be explored. The system described in this paper, called Lyricos, allows for arbitrary lyric input and a fine degree of dynamic control of the voice. In addition, it is able to synthesize a voice that captures voice identity ....
M. W. Macon, L. Jensen-Link, J. Oliverio, M. A. Clements, and E. B. George, "A singing voice synthesis system based on sinusoidal modeling," in Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 435--438, May 1997. Presented at 103rd Meeting of the AES, Sept. 1997 -- AES Preprint 4591 8
An Enhanced ABS/OLA Sinusoidal Model For Waveform Synthesis In.. - Macon, Clements Self-citation (Macon Clements) (Correct)
....and amplitudes in such a way that the fundamental frequency is modified while the general spectral shape is maintained [2] 1.1. Application to TTS In previous work, we described the incorporation of ABS OLA into systems for concatenative speech synthesis [6, 7] and singing voice synthesis [8]. In this approach, the unit inventory of the synthesizer is stored as sets of ABS OLA model parameters instead of as waveforms. To synthesize a new utterance, the model parameters for the sequence of concatenated units are extracted from the inventory and used to generate the pitch and ....
....of uniformly stretching the burst and closure. The duration of a signal is expanded in ABS OLA synthesis by lengthening each synthesis frame by the desired time stretch factor. For moderate duration stretch factors, this approach is adequate. However in some applications (e.g. singing synthesis [8]) a single segment may need to be lengthened by a much greater factor, and it becomes undesirable to compute very long synthesis frames. In these cases, we have employed a looping strategy that repeats a few frames from the center of the segment (usually a vowel) A better approach, reported in ....
M. W. Macon, L. Jensen-Link, J. Oliverio, M. A. Clements, and E. B. George, "A singing voice synthesis system based on sinusoidal modeling," in Proc. ICASSP, vol. 1, pp. 435--438, May 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC