Thesis (Ed. D.)--Teachers College, Columbia University. / Typescript. Sponsor: Harry R. Wilson. Dissertation Committee: Phil C. Lange. Type C project. Includes bibliographical references (leaves [347]-350).

Dissertation (D.M.A.)--The University of North Carolina at Greensboro, 2009. / Directed by Robert Wells; submitted to the School of Music. Title from PDF t.p. (viewed Apr. 29, 2010). Includes bibliographical references (p. 63-66).

Thesis--University of Iowa. / "Reprinted from Psychological review monograph. 69." Includes bibliographical references (p. 65-66).

Throughout our history, the singing voice has been a fundamental tool for musical expression. While analysis and digital synthesis techniques have been developed for normal speech, few models and techniques have been focused on the singing voice. The central theme of this research is the development of models aimed at the characterization and synthesis of the singing voice. First, a spectral model is presented in which asymmetric generalized Gaussian functions are used to represent the formant structure of a singing voice in a flexible manner. Efficient methods for searching the parameter space are investigated and challenges associated with smooth parameter trajectories are discussed. Next a model for glottal characterization is introduced by first presenting an analysis of the relationship between measurable spectral qualities of the glottal waveform and perceptually relevant time-domain parameters. A mathematical derivation of this relationship is presented and is extended as a method for parameter estimation. These concepts are then used to outline a procedure for modifying glottal textures and qualities in the frequency domain. By combining these models with the Analysis-by-Synthesis/Overlap-Add sinusoidal model, the spectral and glottal models are shown to be capable of characterizing the singing voice according to traits such as level of training and registration. An application is presented in which these parameterizations are used to implement a system for singing voice enhancement. Subjective listening tests were conducted in which listeners showed an overall preference for outputs produced by the proposed enhancement system over both unmodified voices and voices enhanced with competitive methods.

Purpose: The purpose of the present study was to examine SLPs' preparation to work with singers by examining their knowledge and training levels regarding vocal hygiene, assessment and treatment for singers, vocal pedagogy and competency in working with singers. Method: A 66-item survey designed to address the research questions was distributed via email to possible participants found through American Speech Language Hearing Association's (ASHA) "Find a Professional" service. Each email contained a password-protected web link to the survey, which was hosted on Survey Monkey. Results: The majority of participants reported low amounts of academic and clinical exposure to singers. The largest percentage demonstrated adequate knowledge of vocal hygiene, but had difficulty with knowledge items regarding assessment and treatment considerations for singers and vocal pedagogy. The majority expressed low levels of competency in working with singers. However, these effects appeared to be mediated by voice specialization. Voice specialists (VS), a subset of the total participants, were found to have received significantly more total hours studying voice and had significantly more voice clients, including singers, than non-voice specialists (NVS). A combination of academic and clinical exposure at the graduate level was found to lead to continued study regarding voice disorders and vocal function for singers. VS also reported higher levels of training in vocal pedagogy and performance and demonstrated significantly higher knowledge levels regarding assessment and treatment considerations for singers and vocal pedagogy than NVS. Similarly, they also reported higher overall competency in working with singers than the NVS. Conclusions: This preliminary data suggests that overall preparation to work with singers is somewhat lacking in most graduate programs. The majority of SLPs appears to retain information regarding vocal hygiene, but does not appear to remember some basic facts about the treatment of voice disorders. Improvements towards education in voice would serve as a worthy goal in improving SLP's service delivery in general to voice clients and singers. Additionally, providing more opportunities to work with voice clients and singers would also help better prepare SLPs as a whole to work with singers. Finally, a structured accreditation process to become a singing voice specialist (SVS) is sorely needed to ensure optimal service delivery to this unique population. / text

Thesis (Ph.D.)--University of Western Sydney, Nepean, 1997. / Includes bibliography.

Extraction of singing voice from music is one of the ongoing research topics in the field of speech recognition and audio analysis. In particular, this topic finds many applications in the music field, such as in determining music structure, lyrics recognition, and singer recognition. Although many studies have been conducted for the separation of voice from the background, there has been less study on singing voice in particular. In this study, efforts were made to design a new methodology to improve the separation of vocal and non-vocal components in audio clips using REPET [14]. In the newly designed method, we tried to rectify the issues encountered in the REPET method, while designing an improved repeating mask which is used to extract the non-vocal component in audio. The main reason why the REPET method was preferred over previous methods for this study is its independent nature. More specifically, the majority of existing methods for the separation of singing voice from music were constructed explicitly based on one or more assumptions.

Zugl.: Heidelberg, Univ., Diss., 2006 u.d.T.: Mecke, Ann-Christine: Der Stimmwechsel und die deutsche Chorpraxis im 18. und 19. Jahrhundert

Singing voice separation (SVS) can be defined as the process of extracting the vocal element from a given song recording. The impetus for research in this area is mainly that of facilitating certain important applications of music information retrieval (MIR) such as lyrics recognition, singer identification, and melody extraction. To date, the research in the field of SVS has been relatively limited, and mainly focused on the extraction of vocals from monophonic sources. The general approach in this scenario has been one of considering SVS as a blind source separation (BSS) problem. Given the inherent diversity of music, such an approach is motivated by the quest for a generic solution. However, it does not allow the exploitation of prior information, regarding the way in which commercial music is produced. To this end, investigations are conducted into effective methods for unsupervised separation of singing voice from stereophonic studio recordings. The work involves extensive literature review of existing methods that relate to SVS, as well as commercial approaches. Following the identification of shortcomings of the conventional methods, two novel approaches are developed for the purpose of SVS. These approaches, termed SEMANICS and SEMANTICS draw their motivation from statistical as well as spectral properties of the target signal and focus on the separation of voice in the frequency domain. In addition, a third method, named Hybrid SEMANTICS, is introduced that addresses time‐, as well as frequency‐domain separation. As there is lack of a concrete standardised music database that includes a large number of songs, a dataset is created using conventional stereophonic mixing methods. Using this database, and based on widely adopted objective metrics, the effectiveness of the proposed methods has been evaluated through thorough experimental investigations.

A canção popular brasileira, principal produto da nossa cultura midiática, vem obtendo reconhecimento nos meios acadêmicos nesses últimos anos, justificando o desenvolvimento de uma prática descritiva que se dedica a analisá-la: a Semiótica da Canção, desenvolvida por Luiz Tatit. Curiosamente, no entanto, o canto popular, principal veículo de manifestação dessa canção, só agora começa a despertar o interesse de pesquisadores. Este trabalho pretende, partindo da aplicação da Semiótica da Canção e a ela acrescentando uma terminologia adequada à percepção descritiva do comportamento vocal, analisar algumas das principais vozes do Brasil, com base na escuta de fonogramas. Procuramos, assim, traduzir o que denominamos Qualidade Emotiva das vozes, na tentativa de desenvolver uma descrição analítica que superasse o juízo de valor ou a mera adjetivação. / During the last years, Brazilian popular song, which are the main product of our media culture, is obtaining recognition among the academic environment, justifying the development of a descriptive practice that is dedicated to analyze it: The Song Semiotics developed by Luiz Tatit. However, it wasnt until now, that popular singing, which is the main means of these songs manifestation, started to awake researchers interest. Starting on The Song Semiotics and adding to it an appropriate term for the descriptive perception of the vocal behavior, this work intend to analyze some of the main Brazilian voices, based on phonograms listening. We will try this way to express what we call Voices Emotive Quality, in an effort to develop an analytic description that overcomes any judgment or mere qualification.