Synthetic Voice

We present an overview of voice AI applied to podcasting to determine whether the current technological offerings pose a threat to audio professionals' jobs, particularly for voice-over artists. To this end, we analyze the main software used by podcast creators for voice cloning and establish a comparative framework. Additionally, we gather creators' perceptions of the results obtained through the analysis of 10 titles

What if a computer, or a machine, teaches us to sing or talk? This photo essay (accompanied by audio files posted on the journal's blog) presents the work undertaken, as part of a practice-as-research PhD, to train in sounding like an artificial voice, with an unusual coach: the computer itself. The project was worked on consistently for months, and this essay explains the pitfalls and frustrations involved in the process, and outlines future possibilities for performing machines differently.

The voice is one of the radio news reader's most important resources when conveying messages. Con trolling the voice, through the proper use of prosodic features as the main tool for transmitting the ex plicit content of a text, provides a referential framework. It is also instrumental in conveying the sense of the text as well as its affective dimension. Ultimately, therefore, it affects the impression forming process of the listener. Therefore, the objective of this study is to contribute to the prosodic characteri sation of radio news by identifying the prosodic resources used. The results show that radio news bul letins can be characterised by a wealth of circumflex contours, regular use of the pitch contour or accent and constant stress on the emphatic accent. Although these resources can guide the discursive under standing of the listener at specific moments during speech, their repeated use can lead to counterpro ductive effects for comprehension and attention.

Studies in different languages have identified a broadcast speaking style, a particular manner that broadcasters have of reading news. This speaking style is characterized by an emphatic intonation with a fast speech rate easily recognizable by listeners. Some authors have stated that messages in this style are not positively perceived by listeners, as it is repetitive and regular, but there is no empirical data to support this conclusion, nor has the style been analyzed with physiological measures. The physiological approach has some advantages, such as a more objective assessment and real-time evaluation. Therefore, this study aims to analyze the effectiveness, adequacy, and physiological response of this broadcast style compared to a narrative pattern. We combined self-report with physiological measures. Fifty-six participants listened to six news pieces in both styles and with two voices, male and female. They had to rate the effectiveness and adequacy of the news while we measu...

This is an Open Access article distributed under the terms of the Creative Commons Attribution-Noncommercial 4.0xUnported License, permitting all non-commercial use, distribution, and reproduction in any medium, provided the original work isproperly cited.

Perceived charisma is an important success factor in professional life. However, women are worse than men in conveying physical charisma signals while at the same time having to perform better than men in order to be perceived equally charismatic. Speech prosody probably contains the most influential charisma signals. We have developed a system called "Pascal" that analyzes and assesses on objective acoustic grounds how well-speakers employ their prosodic charisma parameters. Pascal is used for charismatic-speech training in 12-weeks and 4-h courses on entrepreneurship and leadership. Comparing the prosodic-charisma scores for a total of 72 participants at the beginning and end of these two course types showed that female speakers start with significantly lower prosodic-charisma scores than male speakers. However, at the end of the 4-h course, female speakers can catch up with their male counterparts in terms of prosodic charisma. At the end of the 12-weeks courses, male speakers keep their lead, but female speakers are able to significantly reduce the prosodic charisma gap to male speakers. Since leadership and entrepreneurship are still male-dominated domains, our results can be seen as an encouragement for women to attend prosodic charisma training. Furthermore, these courses require a gender-specific design as we found men to improve mainly in F0 parameters and women in duration and phonation parameters.

A leader's charisma is conveyed by various multiple aspects of his perceivable behavior among which the acousticprosodic characteristics of speech. We present here a study on the perception of charisma in political speech that aims to investigate the notion of charisma and to validate a theoretical framework on a multidimensional scale of charisma perception. The study points out that a multidimensional approach of charisma allows to better analyze which factors are related to specific aspects of speech. We finally clustered the charismatic voice of an Italian political leader in three factors: Proactive-Attracting, Benevolent-Competent and Authoritarian.

A leader's charisma is conveyed by various multiple aspects of his perceivable behavior among which the acousticprosodic characteristics of speech. We present here a study on the perception of charisma in political speech that aims to investigate the notion of charisma and to validate a theoretical framework on a multidimensional scale of charisma perception. The study points out that a multidimensional approach of charisma allows to better analyze which factors are related to specific aspects of speech. We finally clustered the charismatic voice of an Italian political leader in three factors: Proactive-Attracting, Benevolent-Competent and Authoritarian.

A leader's charisma is conveyed by various multiple aspects of his perceivable behavior among which the acousticprosodic characteristics of speech. We present here a study on the perception of charisma in political speech that aims to investigate the notion of charisma and to validate a theoretical framework on a multidimensional scale of charisma perception. The study points out that a multidimensional approach of charisma allows to better analyze which factors are related to specific aspects of speech. We finally clustered the charismatic voice of an Italian political leader in three factors: Proactive-Attracting, Benevolent-Competent and Authoritarian.

Informed by my first six months of doctoral research, this paper offers a topography of virtual influencers that at once acknowledges their continuation of and breaking with the precedents of a lineage of “virtual beings” who have achieved celebrity status. Responding to the ahistoricism of much recent commentary, it draws on archival press and web research to situate virtual influencers at the intersection of technological advancements, discourses, and anxieties similarly characterising Hollywood’s “synthespians” at the turn of the twenty-first century; the legacy of “virtual idols” in East Asia (also known as “Vocaloids” in Japan); and the latter’s recent democratisation by a new generation of “vTubers” across video-sharing sites. Recognising this cross-medium migration of virtual celebrity—from anime, video games and blockbuster cinema to the participatory web—this paper adopts a platform-specific lens to highlight the affordances, cultures and vernaculars of specific social medi...

Many users are exposed every day to artificial voices in their different devices. Because of this, there is a growing interest both in improving the quality of these voices and in analyzing how they are perceived and processed. However, very little research has been conducted to examine nonverbal elements such as prosody. Accordingly, the first purpose of this study is to determine how artificial voices compared to human voices are processed in a narrative advertising story modifying prosody regarding effectiveness, attention, concentration, and recall. The second objective is to evaluate their functions for different applications, advertising among them. The results show that human voices are assessed as more effective and achieved a better level of effectiveness, attention, and recall with less concentration. Concerning the functions, the more important and complex a function is, the more a human voice is preferred over an artificial one.

Cet article dresse un bilan des travaux et expérimentations illustrant les avancées dans le domaine de l'usage de technologies de synthèse vocale pour l'apprentissage de l'écrit. Travailler ou retravailler son écrit, en ayant la possibilité de se corriger autant de fois qu'on le souhaite à l'aide de la voix de synthèse, permet de développer une gestion autonome, par les élèves, de leur apprentissage. Nous faisons le point sur les avantages et les limites de cet outil, en apportant également quelques éléments sur les modalités d'utilisation qui pourraient en être faites.

The charisma of the leader is conveyed through multiple aspects: his ideas and vision and his perceivable verbal and non verbal behaviors. Among these perceivable behaviors there are the acoustic characteristics of speech. We present here a study on the perception of charisma in political speech. We collected speech statements with different illocutionary value taken from two speeches

I will give the following talk at the Symposium, Music and Words at the Royal Central School of Speech and Drama on 26 & 27 June 2015. (http://www.cssd.ac.uk/event/songart-symposium-what-distinctive-about-lyric-performance)
It will serve to introduce three performances:
Kabara’s Lullaby II. (Kabara’s Lullaby I may be heard: http://paulalanbarker.net/id5.html)

Three Songs for Sylvia. (http://paulalanbarker.net/id13.html)

Of Zoe and the Woman I Sing. (excerpt; to be premiered: http://www.tete-a-tete.org.uk/the-artist-his-muse-the-singer-and-her-lover/)

IN MEMORIAM

La présente réédition du dernier cours de maîtrise de Jacques Teyssier pour le Colloque de l’Association Internationale de Psychomécanique du Langage de Juin 2015 à Québec, Université Laval se veut être un hommage à un chercheur parti trop vite à l’âge de 47 ans.

J’étais à l’époque en train de traverser les USA en bus pour visiter diverses personnes et quelques villes. J’apprendrai cette nouvelle à mon arrivée à Davis en Californie où le Professeur Cazemajou était arrivé avant moi.

Connaissant les recherches que Jacques Teyssier faisait j’ai tenté de contacter sa veuve pour récupérer ses papiers de recherche. Je n’ai jamais pu établir le contact que ce soit à son adresse à La Teste ou par les services afférents de l’Université de Bordeaux III, y compris avec l’aide du Professeur Michel Perrin. Il y a ainsi des secrets qui se gardent bien.

Son travail principal de recherche concernait le système de l’article dans les langues germaniques. La perte de ce travail est inestimable.

Dr Jacques COULARDEAU

L'étude a pour but  de mettre en relief  le rôle syntactico-sémantique de la joncture et de la jonction, comme deux phénomènes phoniques,  à la compréhension de l'énoncé français et à en préciser le contenu.
On a donc analysé l'influence de  la jointure et/ou la jonction à plusieurs niveaux: entre deux syllabes, entre deux lexèmes et entre deux groupes rythmiques ou syntaxiques dans la chaine parlée. Cette analyse a montré que la joncture et /ou la jonction jouent un rôle démarcatif:
- en aidant le sujet parlant ou l'auditeur à retrouver et isoler les unités porteuses du sens dans la chaîne parlée;
- en levant l'ambiguïté d'un énoncé, d'un groupe syntaxique ou d'un syntagme à l'aide soit d'une pause (joncture) ou d'une liaison (jonction).

In this paper, the phenomenon of virtual idol Hatsune Miku will be analyzed in the context of critical theory, emerging technologies, and theory of digital art practices. The first part focuses on the phenomenon of the virtual celebrity seen as Deleuze and Guattari’s concept of ‘body without organs.’ The second part examines how the state-of-the-art technologies have enabled the existence of Hatsune Miku who is simultaneously a corporate software product, a pop icon, a performance artist, and a collaborative multimedia artwork. Based on the reading of Hatsune Miku as a hybrid product emerging from the fusion of arts and IT, the last part revolves around the concept of ‘aura’ (Benjamin) generated by virtual idol’s presence. Finally, the notion of hyperterminality is introduced not only to differentiate between entities/identities appearing on the surface of the screen and those virtual constructs co-existing with us in the spaces of physical reality, but also to explore how these newly emerging “phygital” entities transform the existing conceptions of body and identity.

Cette grammaire de 301 pages et de 153 153 mots (dixit Word) fut commandée par un éditeur pour le public des étudiants préparant le CAPES ou l’Agrégation, ainsi que les professeurs du secondaire. Il ne fut pas publié.

Un autre éditeur accepta de regarder le manuscrit mais d’emblée dit que les normes sur la « gratuité » des citations était un obstacle car toutes les citations étant d’auteurs réels et bien placés sur la scène de l’édition américaine ou anglaise, on devait largement dépasser les cinquante lignes « gratuites » par auteur.

L’ensemble de cette grammaire a été mis en ligne sur le site de l’Université de Paris 1 Panthéon Sorbonne, à disposition gratuite pour les étudiants en 2007 (et doit toujours y être) après avoir été mis à disposition informatique gratuite des étudiants de l’IUP Tourisme de l’Université de Perpignan à Mende (Lozère) en 2002-2003.

Jackendoff a beaucoup travaillé sur la musique, mais n’a jamais saisi la différence entre musique et langage, même s’il a atteint la conclusion que l’on ne pouvait pas appliquer l’axiomatique générativiste à la musique. C’est qu’il a manqué tout ce que nous venons de dire, à savoir que c’est l’architecture, donc la syntaxe, qui domine la langue, comme la musique, même si les deux architectures ne sont pas les mêmes, même si, par la voix chantée, on peut les conjuguer ensemble.
« In trying to write a grammar that accounted for the musical intuitions of an educated listener, Lerdahl and I found it impossible to write an algorithm parallel to a tranformational grammar that would generate all and only the possible pieces of tonal music with correct structures. » (Jackendoff, 1997, p 44-45)

RÉFÉRENCES

———, Merriam-Webster’s Collegiate Dictionary, Tenth Edition, Merriam-Webster, Incorporated, Springfield, Massachusetts, 1999
Africa, Frank, in Mumia, Abu-Jamal, 1995
Alex, T.S., Mind Mine, recueil de poésies autoédité, San Antonio, Texas, 1999
Bellow, Saul, Ravelstein, Viking, New York, 2000
BizRate.com®, Online Research Panel, Official Sweepstakes Rules, The Internet, Los Angeles, 2000
Borland, Hal, When the Legends Die, Bantam, New York, 1984
Bunyan, John, The Pilgrim’s Progress, Whitaker House, New York, 1981
Burghardt DuBois, W.E., The Souls of Black Folks, Fawcette Publications, Greenwich, Connecticut, 1961
Chapman, Robert L., PhD, American Slang, Harper and Row, New York, 1987
Conrad, Earl, The Premier, Lancer Books, New York, 1963
Coulardeau, Jacques, « Le passif dans les notices techniques grand public du matériel audiovisuel Kenwood », in Asp n°15-18, GERAS, Bordeaux, 1998
Dickens, Charles, The Mystery of Edwin Drood, OUP, Oxford, 1956
Drapeau, Louis L., The Future of Risk Management : Are You Reading the Signs of the Times ?, The Internet, 2000
Ellis, Bret Easton, American Psycho, Picador, Londres, 1991
Ellison, Ralph, Juneteenth, Vintage International, New York, 1999
Garland, Alex, The Beach, Penguin Books, Londres, 1996
Goddard, Robert, Set in Stone, Bantam, Londres, 1999
Harris, Robert, Archangel, Jove Books, New York, 1999
Hawthorne, Nathaniel, The Scarlet Letter, Washington Square Press, New York, 1970
Hodge, John, The Beach A Screenplay, Faber & Faber, London, 2000
Huebner, Andrew, American by Blood, Anchor, Londres, 2000
Hull, Raymond, « Introduction », in Peter, Dr Laurence J., 1970
Joyce, James, Ulysses, Penguin, Londres, 1975
Marlowe, Christopher, Doctor Faustus, Manchester University Press, Manchester, 1993
Mumia, Abu-Jamal, Live from Death Row, Avon Books, New York, 1995
Murdoch, Iris, Bruno’s Dream, Dell Publishing Company, New York, 1970
Murdoch, Iris, The Green Knight, Chatto and Windus, Londres, 1993
Peter, Dr Laurence J., The Peter Principle, Bantam, New York, 1970
Reed, Ishmael, The Free-Lance Pallbearers, Bantam, New York, 1967
Rice, Anne, The Queen of the Damned, Futura, Londres, 1990
Seeger, Pete, American Favorite Ballads, Oak Publications, New York, 1961
Shakespeare, William, Antony and Cleopatra, Spring Books, Londres, 1965
Skeat, Walter W., Concise Etymological Dictionary of the English Language, Oxford University Press, Oxford, 1965
Taylor, Richard J., « The Art of Digital Techniques in the Broadcast Studio », SMPTE, Scarsdale, New York, 1982
Townsend, Sue, The Diary of Adrian Mole, Aged 13¾, Methuen, Londres, 1982
Tropper, Jonathan, Plan B, St Martin’s Press, New York, 2000
Walker, Margaret, Jubilee, Bantam, New York, 1