Un nombre croissant d'études révèle combien les processus cérébraux de production et de perception de l'action sont intriqués. En particulier, on sait maintenant que la perception de la parole induit l'activation de représentations motrices articulatoires chez l'auditeur. Dans ce travail, nous explorons la perception de la voix chantée, une action vocale non-linguistique. L'écoute d'une voix chantée provoque-t-elle une activation du système moteur ? Cette activité motrice est-elle plus forte pour la voix que pour un son musical non-biologique ? Ces questions sont abordées en utilisant de façon complémentaire deux protocoles comportementaux, une technique de lésion virtuelle par stimulation magnétique transcrâniale, l'étude des oscillations en EEG et celle de la variabilité métabolique en IRMf. Nos résultats montrent que la perception d'une voix chantée est effectivement associée à une activité du cortex sensorimoteur dans des tâches de répétition et de discrimination. De façon intéressante, les plus mauvais chanteurs ont montré la plus forte résonance motrice. Le système moteur pourrait, par la génération de modèles internes, faciliter le traitement des stimuli ou la préparation de la réponse vocale quand le traitement acoustique seul est insuffisant. L'ensemble des résultats présentés ici suggère que les interactions audiomotrices en perception de la voix humaine sont modulées par la dimension biologique du son et par le niveau d'expertise vocale des auditeurs. / A growing body of research reveals that action production and action perception interact. In particular, it has been shown that speech perception entails articulatory motor representations in the listener. In the present work, we investigate the perception of a singing voice, a stimulus that is not primarily linked to articulatory processes. Does listening to a singing voice induce activity in the motor system? Is this motor activity stronger for a voice than for a non-biological musical sound? Two behavioral tasks, a og virtual lesionfg{} paradigm using TMS, the study of brain oscillations with EEG and an fMRI experiment carried out during my PhD have shed some light on these questions. Our results show that the perception of a singing voice is indeed associated with sensorimotor activity in repetition and discrimination tasks. Interestingly, the poorer singers displayed the stronger motor resonance. The motor system could facilitate the processing of sound or the preparation of the vocal response by internal model generation when the acoustic processing is not effective enough. The set of studies presented here thus suggests that audiomotor interactions in human voice perception are modulated by two factors: the biological dimension of sound and the listeners' vocal expertise. These results suggest new perspectives on our understanding of the auditory-vocal loop in speech and of sound perception in general.

Made available in DSpace on 2016-08-17T14:52:55Z (GMT). No. of bitstreams: 1 Paulo Henrique Bezerra de Carvalho.pdf: 6145212 bytes, checksum: 1f5a8a10fa0d0e9f555a3fe1f67ac240 (MD5) Previous issue date: 2003-12-12 / This work proposes an speech signal encoder variation based on two concepts: the formants and the modulating components of the speech signal. The method suggested for the codification extracts the modulating components (instantaneous amplitude and frequency) to be transmitted. The method is based on the fact that the transmission of the speech can be substituted by the transmission of its AM-FM modulating components (amplitude modulation - frequency modulation). Thus, to send such components, the LPC (linear predictive coding) method is used to determine the frequencies that correspond to the first four formants of the speech spectrum within a 4 kHz band. Then, through a modified Gabor s wavelet function, four narrow bands are filtered around the formants. Finally, the properties of the Hilbert transform are used to determine the modulating components of the filtered bands, in other words, the instantaneous amplitudes and frequencies. The final result is the codification of eight signals in which four of them correspond to the instantaneous amplitudes and the other four correspond to the instantaneous frequencies. It is also presented a recovery of human speech where tests of intelligibility of the samples are applied after their respective recoveries. The results obtained showed that the method is a promising technique to be implemented in actual applications. / Este trabalho propõe uma variação de codificador do sinal de voz baseada em dois conceitos: os formantes e as componentes modulantes do sinal. O método proposto de codificação extrai as componentes modulantes (amplitudes e freqüências instantâneas) para serem transmitidas. O método é baseado no fato de que a transmissão da voz pode ser substituída pelo envio de suas componentes modulantes AM-FM (amplitude modulation - frequency modulation). Desse modo, para o envio de tais componentes é utilizado o método LPC (linear predictive coding) para a determinação das freqüências correspondentes aos quatro primeiros formantes do espectro de voz na faixa de 4 kHz. Em seguida, através de uma função wavelet modificada de Gabor, são filtradas quatro faixas estreitas em torno desses formantes. Por último, utilizando-se as propriedades da transformada de Hilbert, são determinadas as componentes modulantes das faixas filtradas, ou seja, as amplitudes e freqüências instantâneas. O resultado final é a codificação de oito sinais, sendo quatro correspondentes às amplitudes instantâneas e quatro das freqüências instantâneas. Também é apresentada a recuperação da voz a partir dos oitos sinais e para a validação do método são utilizadas cinco amostras de voz humana onde são empregados testes de inteligibilidade das amostras após as suas respectivas recuperações. Os resultados obtidos mostraram que o método é factível de implementação em aplicações reais.

In the first part of this master's thesis there is briefly presented the biomechanics of the human voice creation and an overview of the hitherto published computational models of the vocal tract and dissemination of the acoustic waves around the human head. The second part of the thesis deals with the creation of the computational model of a dissemination of the acoustic waves through vocal tract and further into a space around the head during the pronouncing of the Czech vowel /a:/. The vocal tract is excited by a harmonic signal in the place of vocal chords. On the surface of the vocal tract and the part of the head including hair and skin there is defined an acoustic absorption. The dissemination of the acoustic waves in the vocal tract, in the near field around the mouth, in the area around the head and in the points on the cheeks is detailed mapped. The dissemination of the acoustic waves is analyzed in the points where the speech microphones are placed. Acoustic pressure dependence on frequency, transmission functions between defined points and the acoustic pressure amplitudes depending on the distance from the mouth are obtained. In particular, the frequency distortion of the spectra is observed at the points indicated. Furthermore, the radiation impedance in the mouth area is evaluated. The results obtained are compared with the results of the hitherto published experimental measurements and can be used for the exact measurement of human voice or for the frequency correction of the microphones during the scann of the speech and sing placced in the analyzed points.

The first part of this work focuses on ways to replace missing source voice in case of patients after total laryngectomy. The commonly used methods of voice rehabilitation are mentioned. Simple computational models are used to explore several principles of generating artificial source voice. Based on the knowledge of how a healthy human voice is generated, one of the ways to generate artificial source voice was chosen – a reed-based element in the configuration (-, +). The function of the reed-based element is based on a periodic bending of the reed and in the airflow cutoff created by this motion. The (-,+) configuration of the reed-based element causes a different behaviour, when compared to healthy vocal folds, important is, however, whether the generated acoustic signal has the right spectral characteristics, which enable the generation of voiced vowels of the human speech. Both experimental and computational models are used to study the behaviour of the reed-based element. The design of the experimental model is based on the preliminary experiments with simple reed-based elements, which were carried out at the beginning of my studies. The new experimental model is designed in such a way, that it enables changes to the reed geometry and its position towards the reed stop. The measurements carried out on the experimental model are mainly acoustical (measurements of the generated acoustical signal), but optical measurements of the reed´s movement and position are possible and used as well. Because of the nature of the reed-based element´s behavior, the fluid structure interaction must be taken into consideration in the computational model. A two-way model of fluid structure interaction is used between the fluid part of the computational model and the structural one. A partitioned solution is used to solve the fluid-structure interaction. The effect of specific input parameters on the function of both models (experimental and computational) is monitored. The influences of input parameters on the basic frequency of the generated signal (source voice), on the stability of the function and on other important characteristics are evaluated. The final chapters focus on the design of voice prosthesis in general. Some specific issues, which need to be solved when designing voice prosthesis, are highlighted.

The link between trumpet playing and emulation of the human voice has been acknowledged by a number of prominent teachers, authors, and composers since the inception of the trumpet as a melodic instrument. This dissertation is a pedagogical guide to lyrical trumpet performance based on the verismo style of singing consistent with the authentic interpretations of operatic soprano arias by Pietro Mascagni, Ruggero Leoncavallo, and Giacomo Puccini. Included are chapters that examine various aspects of the verismo style, as well as comparison and application of late 19th-century voice pedagogy to trumpet practice and performance. This resource examines six recordings of sopranos who created or popularized operatic roles during the verismo period. Included are transcriptions of the six arias for trumpet and piano, with performance notes based on dramatic and textual contexts, as well as interpretive aspects, namely tempo, dynamics, and vibrato.

本研究主要探討Facebook企業粉絲頁進行危機溝通之效果。由於企業粉絲頁在訊息與互動策略上都與傳統官方網站截然不同，其中如同朋友般對話口吻的「人性化語調」（conversational human voice），可說是現今國內企業粉絲頁的主要溝通特色。然而，在危機溝通的情境下，企業粉絲頁卻往往採用官方口吻，使用較傳統的新聞稿模式，似乎未因應粉絲頁特性而採取相適的溝通策略，其溝通效果如何值得加以探討。同時，綜觀過去危機溝通文獻，多數研究仍聚焦於驗證危機情境與回應策略間對應關係，預測危機溝通效果的實用性，並未深入討論訊息策略的內容，也尚未有粉絲頁平台上的效果研究。因此，本論文即以「人性化語調」的概念切入，檢視該訊息策略於危機情境中的溝通效果，以探討企業於粉絲專頁上進行危機溝通的可能之有效策略，以及企業於社群媒體進行危機溝通之可行性。 實驗設計主要以「產品瑕疵」為危機情境，三個操弄變項包含危機責任程度（小╱大）、回應策略（遞減╱重建）、與人性化語調（低╱高），以2 × 2 × 2之組間設計實驗設計，驗證危機溝通的效果（組織聲譽，正負面口碑行為意向）。 研究結果發現，不論組織責任大小，重建策略皆帶來正面溝通效果；而人性化語調雖然在組織聲譽、正面口碑行為意向上無顯著的效益，但能有效減緩負面口碑行為意向，尤其在危機責任大的情境下，採取重建策略與人性化語調高的溝通組合能更加強其緩和負面口碑行為之成效。顯示危機回應策略相關理論在企業粉絲專頁的情境依然適用，但在具體溝通策略與內容的設計上，必須進一步考量危機情境與所使用之溝通平台，也表示國內企業對於社群媒體之公關管理必須加以重視。 / “Conversational human voice” is one of the key features in how Taiwan’s corporations communicate on their Facebook fanpages, which is quite different from how they communicate on their corporate websites. And yet, how such communication strategies work during a time of crisis remains unknown; thus, the current study aims to investigate the effect of conversational human voice in the scope of crisis communication. In the experimental design, the independent variables included: human voice (low/high), crisis responsibility (low/high), and crisis communication strategy (diminish/rebuild); the dependent variables included corporate reputation and word-of-mouth (WOM) intentions. The key finding included positive effects of constructive strategies on corporate reputation and WOM intentions, which is consistent with past literature. Although human voice was found with no main effects on reputation or WOM intentions, human voice was effective in reducing negative WOM, when the crisis responsibility was high and constructive communication strategy was employed. This implies that consumers who are exposed to more human-tone messages on the fanpages are less likely to boycott the product should there be a relevant crisis, and thus, social media play an important role in crisis communication and should be valued and managed in corporate public relations efforts.

This doctoral thesis focuses on computational modelling of human vocal folds and vocal tract functions using finite element method (FEM). Human voice is crucial in human communication. Therefore one of the main targets of current medicine is creation of artificial vocal folds, which would substitute the original vocal folds. The computational modelling can be used to understand principles of voice production, determination of parameters that the artificial vocal folds have to meet and verification of their functionality. First part of this thesis focuses on modelling of human voice creation by whisper. Influence of intraglottal gap on eigenvalues distribution for individual vowels was analysed using FEM vocal tract and trachea model. Further there is presented two-dimensional (2D) finite element model of the flow-induced self-oscillation of the human vocal folds in interaction with acoustic spaces of the vocal tract. The 2D vocal tract model was created on the basis of converting the data from magnetic resonance images (MRI). Explicit coupling scheme with separated solvers for structure and fluid domain was used for modelling of the fluid-structure interaction. Created computational model comprises: large deformations of the vocal folds tissue, contact between vocal folds, fluid-structure interaction, morphing the fluid mesh according to the vocal-fold motion (Arbitrary Lagrangian-Eulerian approach), unsteady viscous compressible or incompressible airflow described by the Navier-Stokes equations and airflow separation during glottis closure. This model is used to analyse the influence of stiffness and damping changes in individual vocal fold tissue layers (in particular in superficial lamina propria). Part of this computational analysis is also comparison of vocal folds behaviour for compressible and incompressible flow model. Videokymograms (VKG) are subsequently created from obtained results of FEM calculations which enable to compare individual variants between themselves and with motion of real human vocal folds. In next part of this thesis is presented three-dimensional (3D) finite element model of the flow-induced self-oscillation of the human vocal folds. This 3D model was created from a previous 2D model by extrude to the third direction. Using this model was again compared influence of compressible and incompressible flow model on vocal folds motion and generated sound by using videokymograms and acoustic spectra. The last part of this thesis focuses on the possibility to replace missing natural source voice in form reed-based element. Behaviour of reed-based element was analysed using computational modelling and using measurements on experimental physical model. The physical model enables changes in setting gap between reed and reed stop and performing acoustical and optical measurements.

Ljudigenkänning möjliggörs genom spektralanalys, som beräknas av den snabba fouriertransformen (FFT), och har under senare år nått stora genombrott i samband med ökningen av datorprestanda och artificiell intelligens. Tekniken är nu allmänt förekommande, i synnerhet inom bioakustik för identifiering av djurarter, en viktig del av miljöövervakning. Det är fortfarande ett växande vetenskapsområde och särskilt igenkänning av fågelsång som återstår som en svårlöst utmaning. Även de främsta algoritmer i området är långt ifrån felfria. I detta kandidatexamensarbete implementerades och utvärderades enkla algoritmer för att para ihop ljud med en ljuddatabas. En filtreringsmetod utvecklades för att urskilja de karaktäristiska frekvenserna vid fem tidsramar som utgjorde basen för jämförelsen och proceduren för ihopparning. Ljuden som användes var förinspelad fågelsång (koltrast, näktergal, kråka och fiskmås) så väl som egeninspelad mänsklig röst (4 unga svenska män). Våra resultat visar att framgångsgraden normalt är 50–70%, den lägsta var fiskmåsen med 30% för en liten databas och den högsta var koltrasten med 90% för en stor databas. Rösterna var svårare för algoritmen att särskilja, men de hade överlag framgångsgrader mellan 50% och 80%. Dock gav en ökning av databasstorleken generellt inte en ökning av framgångsgraden. Sammanfattningsvis visar detta kandidatexamensarbete konceptbeviset bakom fågelsångigenkänning och illustrerar såväl styrkorna som bristerna av dessa enkla algoritmer som har utvecklats. Algoritmerna gav högre framgångsgrad än slumpen (25%) men det finns ändå utrymme för förbättring eftersom algoritmen vilseleddes av ljud av samma frekvenser. Ytterligare studier behövs för att bedöma den utvecklade algoritmens förmåga att identifiera ännu fler fåglar och röster. / Sound recognition is made possible through spectral analysis, computed by the fast Fourier transform (FFT), and has in recent years made major breakthroughs along with the rise of computational power and artificial intelligence. The technology is now used ubiquitously and in particular in the field of bioacoustics for identification of animal species, an important task for wildlife monitoring. It is still a growing field of science and especially the recognition of bird song which remains a hard-solved challenge. Even state-of-the-art algorithms are far from error-free. In this thesis, simple algorithms to match sounds to a sound database were implemented and assessed. A filtering method was developed to pick out characteristic frequencies at five time frames which were the basis for comparison and the matching procedure. The sounds used were pre-recorded bird songs (blackbird, nightingale, crow and seagull) as well as human voices (4 young Swedish males) that we recorded. Our findings show success rates typically at 50–70%, the lowest being the seagull of 30% for a small database and the highest being the blackbird at 90% for a large database. The voices were more difficult for the algorithms to distinguish, but they still had an overall success rate between 50% and 80%. Furthermore, increasing the database size did not improve success rates in general. In conclusion, this thesis shows the proof of concept and illustrates both the strengths as well as short-comings of the simple algorithms developed. The algorithms gave better success rates than pure chance of 25% but there is room for improvement since the algorithms were easily misled by sounds of the same frequencies. Further research will be needed to assess the devised algorithms' ability to identify even more birds and voices.