Classification of the Classical Male Singing Voice Using Long-Term Average Spectrum
23
Citation
18
Reference
10
Related Paper
Citation Trend
Keywords:
Vibrato
Sample (material)
This paper presents a singing synthesis system,VocaListener, that automatically estimates parameters for singing synthesis from a user’s singing voice with the help of song lyrics. Although there is a method to estimate singing synthesis parameters of pitch (F 0 ) and dynamics (power) from a singing voice, it does not adapt to different singing synthesis conditions (e.g., different singing synthesis systems and their singer databases) or singing skill/style modifications. To deal with different conditions, VocaListener repeatedly updates singing synthesis parameters so that the synthesized singing can more closely mimic the user’s singing. Moreover, VocaListener has functions to help modify the user’s singing by correcting off-pitch phrases or changing vibrato. In an experimental evaluation under two different singing synthesis conditions, our system achieved synthesized singing that closely mimicked the user’s singing.
Vibrato
Lyrics
Cite
Citations (45)
MiruSinger is a singing skill visualization interface that analyzes and visualizes vocal singing in reference to the vocal-part of music CD recordings. The system focuses on visualizing the characteristics of singing skills with real- time feedback. Although there are previous systems for singing training assistance that provide real-time visual feedback of the singing voice, none had utilized real-world (commercial) recordings as referential data. MiruSinger has the capability of visualizing F0 (fundamental fre- quency) and vibrato sections of the user's singing voice in real-time, showing comparison with the estimated F0 tra- jectory of the vocal-part in music CD recordings. The ex- tracted F0 trajectory can be hand-corrected to improve ref- erential quality. A trial usage of the system shows that it would be a useful tool for average users, and that the sys- tem itself is entertaining and fun for the users.
Vibrato
Interface (matter)
Auditory feedback
Cite
Citations (1)
MiruSinger is a singing skill visualization interface that analyzes and visualizes vocal singing in reference to the vocal-part of music CD recordings. The system focuses on visualizing the characteristics of singing skills with real- time feedback. Although there are previous systems for singing training assistance that provide real-time visual feedback of the singing voice, none had utilized real-world (commercial) recordings as referential data. MiruSinger has the capability of visualizing F0 (fundamental fre- quency) and vibrato sections of the user's singing voice in real-time, showing comparison with the estimated F0 tra- jectory of the vocal-part in music CD recordings. The ex- tracted F0 trajectory can be hand-corrected to improve ref- erential quality. A trial usage of the system shows that it would be a useful tool for average users, and that the sys- tem itself is entertaining and fun for the users.
Vibrato
Interface (matter)
Cite
Citations (20)
In this paper, a template-based personalized singing voice synthesis method is proposed. It generates singing voices by means of conversion from the narrated lyrics of a song with the use of template recordings. The template voices are parallel speaking and singing voices recorded from professional singers, which are used to derive the transformation models for acoustic feature conversion. When converting a new instance of speech, its acoustic features are modified to approximate those of the actual singing voice based on the transformation models. Since the pitch contour of the synthesized singing is derived from an actual singing voice, it is more natural than modifying a step contour to implement pitch fluctuations such as overshoot and vibrato. It has been shown from the subjective tests that nearly natural singing quality with the preservation of the timbre can be achieved with the help of our method.
Vibrato
Timbre
Lyrics
Feature (linguistics)
Pitch contour
Cite
Citations (22)
Vocal tract
Vocal music
Cite
Citations (38)
Vibrato is one of the important marks of art singing voice.In view of the current confusing cognition situation of domestic vocal field,it is necessary to learn more about the specific producing process and principles of vibrato,which has a positive sense for promoting the development of singing skills and improving teaching and means.
Vibrato
Cite
Citations (0)
This paper compared the singing voices of four student singers of Chinese national singing before and after vocal warm-up. Statistics showed that the parameters such as deviation from the standard note, vibrato rate and jitter were undergoing significant changes after 30 minutes of warming up exercise, while the differences of vibrato extent demonstrated a controversy result. Overall, this paper indicated that, all of the participants benefited from vocal warm-up by increasing accuracy of singing tone heights, decreasing jitters and approximating their vibrato rates to the moderate range of western singing style.
Vibrato
Tone (literature)
Cite
Citations (0)
This dissertation is concerned with the problem of describing the singing voice within the audio signal of a song. This work is motivated by the fact that the lead vocal is the element that attracts the attention of most listeners. For this reason it is common for music listeners to organize and browse music collections using information related to the singing voice such as the singer name. Our research concentrates on the three major problems of music information retrieval: the localization of the source to be described (i.e. the recognition of the elements corresponding to the singing voice in the signal of a mixture of instruments), the search of pertinent features to describe the singing voice, and finally the development of pattern recognition methods based on these features to identify the singer. For this purpose we propose a set of novel features computed on the temporal variations of the fundamental frequency of the sung melody. These features, which aim to describe the vibrato and the portamento, are obtained with the aid of a dedicated model. In practice, these features are computed on the time-varying frequency of partials obtained using the sinusoidal model. In the first experiment we show that partials corresponding to the singing voice can be accurately differentiated from the partials produced by other instruments using decisions based on the parameters of the vibrato and the portamento. Once the partials emitted by the singer are identified, the segments of the song containing singing can be directly localized. To improve the recognition of the partials emitted by the singer we propose to group partials that are related harmonically. Partials are clustered according to their degree of similarity. This similarity is computed using a set of CASA cues including their temporal frequency variations (i.e. the vibrato and the portamento). The clusters of harmonically related partials corresponding to the singing voice are identified using the vocal vibrato and the portamento parameters. Groups of vocal partials can then be re-synthesized to isolate the voice. The result of the partial grouping can also be used to transcribe the sung melody. We then propose to go further with these features and study if the vibrato and portamento characteristics can be considered as a part of the singers' signature. Previous works on singer identification describe audio signals using features extracted on the short-term amplitude spectrum. The latter features aim to characterize the timbre of the sound, which, in the case of singing, is related to the vocal tract of the singer. The features we develop in this document capture long-term information related to the intonation of the singer, which is relevant to the style and the technique of the singer. We propose a method to combine these two complementary descriptions of the singing voice to increase the recognition rate of singer identification. In addition we evaluate the robustness of each type of feature against a set of variations. We show the singing voice is a highly variable instrument. To obtain a representative model of a singer's voice it is thus necessary to build models using a large set of examples covering the full tessitura of a singer. In addition, we show that features extracted directly from the partials are more robust to the presence of an instrumental accompaniment than features derived from the amplitude spectrum.
Vibrato
Cite
Citations (2)
AT RECENT CONFERENCE OF VOICE TEACHERS, I attended a discussion on differences between choral and solo singing techniques led by a panel of widely respected university choir directors and voice professors. The panelists discussed how singing in ensembles affects vocal technique, especially with regard to nonvibrato singing. With the audience, they shared the opinion that choral singing should be colorful and vibrant, and implied that singing without vibrato is harmful to the voice. None defended the idea that there may be value in different styles of voice production, or that voice teachers have a responsibility to equip their students to sing them. One of the panelists remarked that, as teachers, our primary motivation should be to give the students what is best for them, and it is at that point where I would like to begin this article. What are the most important underlying issues of this controversy, and how will our responses to them best serve our students? The first issue is that of aesthetic preference; the second is that of vocal health. In this discussion, the latter shall be addressed first, as we can appeal to voice science to answer the question, Does singing without vibrato ruin the voice? shares certain characteristics with art and the weather, about which there have been witty comments throughout history. We may not know all the facts of the matter, but we do know what we like. Meribeth Bunch notes that [c]onsiderable acoustic research has been directed toward vibrato, yet virtually nothing is known about the physiological mechanism that produces it.1 She and William Vennard adopt Seashore's 1938 definition of a good vibrato as a pulsation of pitch usually accompanied with synchronous pulsations of loudness and timbre [that] give a flexibility, tenderness and richness to the tone.2 Most voice scientists agree that from five to eight pulsations per second constitute what today is considered a pleasing vibrato; fewer than five are usually considered a wobble, whereas more than eight approach what we call a tremolo. Taste affects vibrato rates. Clifton Ware notes: Aesthetic tastes for vibrato patterns tend to vary ... from the minimal vibrato of early choral singers to the fast vibrato patterns prevalent among opera singers in the early twentieth century.3 The rate of singers' vibrato also varies depending on the type of music being sung and the dynamic level required. As Ware quotes Ingo Titze: Vibrato increases with vocal intensity, as when singing a crescendo ... frequency appears to increase slightly with rising pitch and a singer's level of excitement.4 Vennard notes: Opera singers have more rapid vibrati than concert singers, as a rule ... Usually the same singer's rate decreases in concert where he does not have to compete in volume with a sixty-piece orchestra.5 Cultural factors come into play. Barbara Doscher remarks: Children in some countries (Austria) sing with vibrato while those in other countries (England) do not.6 Nicholas Isherwood notes: Extensive travels by this author have confirmed that singers from virtually all cultures outside of Europe and North America sing with no vibrato, as do North American natives,7 and points the reader to recordings and spectral analyses for examples of such styles of singing.8 Although some voice pedagogues believe that nonvibrato singing is harmful, there doesn't seem to be much research to support their contention. Ware states: Excessive straight-tone singing can retard the vocal development of young singers,9 but does not offer any scientific corroboration. James McKinney cites one study by John Large and Shigenobu Iwata that suggests vibrato prevents laryngeal fatigue.10 Vennard does not care for straight-tone singing, but doesn't claim it is injurious to the voice, even admitting that it has its place. Discussing the historical arguments, he says, A cultivated singer [of the Renaissance era] could alternate straight tones and tones with vibrato at will-a useful skill today in fact. …
Vibrato
Choir
Vocal music
Nothing
Cite
Citations (13)
MiruSinger is a singing skill visualization interface that analyzes and visualizes vocal singing in reference to the vocal-part of music CD recordings. The system focuses on visualizing the characteristics of singing skills with real- time feedback. Although there are previous systems for singing training assistance that provide real-time visual feedback of the singing voice, none had utilized real-world (commercial) recordings as referential data. MiruSinger has the capability of visualizing F0 (fundamental fre- quency) and vibrato sections of the user's singing voice in real-time, showing comparison with the estimated F0 tra- jectory of the vocal-part in music CD recordings. The ex- tracted F0 trajectory can be hand-corrected to improve ref- erential quality. A trial usage of the system shows that it would be a useful tool for average users, and that the sys- tem itself is entertaining and fun for the users.
Vibrato
Interface (matter)
Cite
Citations (4)