Voice Type Research Articles

Voice Command Recognition for Movement Control of a 4-DoF Robot Arm

Robots are widely used in industry. Robots generally have a control system or intelligence embedded in the processor. The robots consist of mobile mode, manipulator, and their combination. Mobile robots usually use wheels, and manipulator robots have limited degrees of freedom. Both have their respective advantages. Mobile robots are widely applied to environments with flat floor surfaces. The manipulator robots are applied to a static environment to produce, print, and cut material. In this study, the robot arm 4 Degree of Freedom (DoF) is integrated with a computer. The computer controls the whole system, where the operator can control the Robot based on voice commands. The operator's voice is one person only with different intonations. Voice command recognition uses the Mel-Frequency Cepstral Coefficients (MFCC) and Artificial Neural Networks (ANN) methods. The MFCC and ANN programs are processed in the computer, and the program output is sent to the Robot via serial communication. There are nine types of voice commands with different MFCC patterns. ANN training data for each command is 10 data, so the total becomes 90. In this experiment, the Robot can move according to voice commands given by the operator. Tests for each voice command are ten experiments, so the total experiment is 90 times with a success rate of 94%. There is only one operator, and experiments have not yet been carried out with the voices of several operators. The error occurred because there were several similar patterns during system testing.

Horizontal and Vertical Voice Directivity Characteristics of Sung Vowels in Classical Singing

Singing voice directivity for five sustained German vowels /a:/, /e:/, /i:/, /o:/, /u:/ over a wide pitch range was investigated using a multichannel microphone array with high spatial resolution along the horizontal and vertical axes. A newly created dataset allows to examine voice directivity in classical singing with high resolution in angle and frequency. Three voice production modes (phonation modes) modal, breathy, and pressed that could affect the used mouth opening and voice directivity were investigated. We present detailed results for singing voice directivity and introduce metrics to discuss the differences of complex voice directivity patterns of the whole data in a more compact form. Differences were found between vowels, pitch, and gender (voice types with corresponding vocal range). Differences between the vowels /a:, e:, i:/ and /o:, u:/ and pitch can be addressed by simplified metrics up to about d2/D5/587 Hz, but we found that voice directivity generally depends strongly on pitch. Minor differences were found between voice production modes and found to be more pronounced for female singers. Voice directivity differs at low pitch between vowels with front vowels being most directional. We found that which of the front vowels is most directional depends on the evaluated pitch. This seems to be related to the complex radiation pattern of the human voice, which involves a large inter-subjective variability strongly influenced by the shape of the torso, head, and mouth. All recorded classical sung vowels at high pitches exhibit similar high directionality.

The effects of vowel, pitch, and dynamics on the emotional characteristics of the Soprano, Alto, Tenor, and Bass Voices

Previous research on the soprano and tenor voices have shown that their emotional characteristics change with different vowel, pitch, and dynamics. This work continues the investigation with the alto and bass voices. Listening tests were conducted whereby listeners gave absolute judgements on the SATB voice tones over ten emotional categories with the data analyzed using logistic regression. High-arousal categories were stronger for loud tones, whereas low-arousal categories were stronger for soft tones. The categories Happy, Heroic, Romantic, and Shy had mostly upward trends across the pitch range, whereas Angry had an overall downward trend. Calm and Sad had an arch-shaped trend, while Scary had a U-shaped trend. Comic and Mysterious had different trends among the voices. The voices each exhibited different vowel trends, though vowel A was dominant for all the voice types in the categories Happy and Romantic. Dynamics had the strongest effect overall, followed closely by pitch, with both effects approximately twice as strong as the effect of vowel. Vowel U had the largest strength-of-expressiveness overall, with A second, O third, I fourth, and finally E last. These results give a quantified preliminary perspective on how vowel, pitch, and dynamics shape emotional expression in the SATB voices.

Listeners’ Attitudes Towards Young Women With Glottal Fry

Glottal fry is an increasingly prevalent voice type in young female speakers. The purpose of this study was to identify employers' perceptions toward young female speakers presenting with glottal fry and the impact on hirability. Sixty employers responsible for hiring at their business in the Southeast region of the United States completed a survey developed to capture employers' perceptions toward young women using glottal fry. Employers listened to three voice samples of young women with varying levels of glottal fry and rated the voice on 14 semantic differential items. The semantic differential items were derived from the hiring constructs literature to capture perceptions related to mental capability, personality tendencies, and applied social skills. Additionally, questions related to hirability were captured at the end of the survey. Employers were able to identify continuous glottal fry compared to nonglottal fry voice samples. Employers rated voice samples with glottal fry more negatively (eg, less trustworthy, less competent, less educated) compared to nonglottal fry voice samples and were less likely to hire female speakers with continuous glottal fry. This study highlights the impact of negative perceptions toward glottal fry on hirability of young female speakers. Such information can provide insight to increase awareness of the impact of a voice type on listener perceptions and communication among young female speakers.

Clefs, Pitch, and Transposition in Vocal Music before 1600

Vocal music of the fifteenth and sixteenth centuries was notated in various combinations of clefs, including standard, high, and low arrays. While the instrumental practice of transposing music written in high clefs down a fourth or fifth in order to accommodate the natural ranges of human voices is amply and unambiguously documented from around 1600 onwards, it is more difficult to prove that a similar practice of adjusting the sounding compass to a normative pitch was applied to earlier vocal polyphony. Theorists from the late fifteenth and the sixteenth centuries, however, agree in recognizing the existence of just four basic male voice types (soprano, alto, tenor, and bass) and in limiting the ordinary compass of vocal music to 19-20 notes-the size of the gamut-a prescription that can only be understood as referring to a range of pitches, no matter on what notes that range might be written. A series of case studies of repertoire composed between 1450 and 1550 confirms that the principle of a limited compass was unfailingly respected in actual music. The only logical conclusion is that, no matter on what notes a piece is written, its sounding pitch was adjusted to a normative level.

Mixed Messages: Why managers (do not) endorse employee voice

We develop and test a theory of how managerial endorsement is influenced by how employees voice their ideas – whether they engage in promotive voice, prohibitive voice, or a mix of these two types together. Drawing on research on cognitive fluency resulting from consistency in information, we argue and show that managers are less likely to endorse voice that mixes both promotive and prohibitive elements within the same instance of speaking up, compared to voice that is uniformly promotive or prohibitive. Extending these arguments about cognitive fluency, we further show that endorsement is contingent on whether each uniform type is consistent with managerial regulatory focus. Our findings, based on five studies – a survey study of managers from a wide range of organizations, a field study in a hospital, and three experiments – enrich our theoretical understanding of the cognitive paths through which the type(s) of voice, and whether voice mixes these types, shapes which ideas are endorsed for implementation. They also reveal important implications for managers about why they may systematically gravitate toward (and miss out on) certain ideas when they evaluate employee voice, and for employees about the tactical choices they should use in voicing ideas to their managers.

Lombard Effect in Individuals With Nonphonotraumatic Vocal Hyperfunction: Impact on Acoustic, Aerodynamic, and Vocal Fold Vibratory Parameters.

This exploratory study aims to investigate variations in voice production in the presence of background noise (Lombard effect) in individuals with nonphonotraumatic vocal hyperfunction (NPVH) and individuals with typical voices using acoustic, aerodynamic, and vocal fold vibratory measures of phonatory function. Nineteen participants with NPVH and 19 participants with typical voices produced simple vocal tasks in three sequential background conditions: baseline (in quiet), Lombard (in noise), and recovery (5 min after removing the noise). The Lombard condition consisted of speech-shaped noise at 80 dB SPL through audiometric headphones. Acoustic measures from a microphone, glottal aerodynamic parameters estimated from the oral airflow measured with a circumferentially vented pneumotachograph mask, and vocal fold vibratory parameters from high-speed videoendoscopy were analyzed. During the Lombard condition, both groups exhibited a decrease in open quotient and increases in sound pressure level, peak-to-peak glottal airflow, maximum flow declination rate, and subglottal pressure. During the recovery condition, the acoustic and aerodynamic measures of individuals with typical voices returned to those of the baseline condition; however, recovery measures for individuals with NPVH did not return to baseline values. As expected, individuals with NPVH and participants with typical voices exhibited a Lombard effect in the presence of elevated background noise levels. During the recovery condition, individuals with NPVH did not return to their baseline state, pointing to a persistence of the Lombard effect after noise removal. This behavior could be related to disruptions in laryngeal motor control and may play a role in the etiology of NPVH. https://doi.org/10.23641/asha.20415600.

The Effects of Anthropomorphism, Message Framing, and Voice Type on Unhealthy Sleep Behavior in Young Users: The Mediating Role of Risk Perception.

Insufficient sleep is a severe social public health problem that can adversely affect the physical and mental health of young people. This study examined risk perceptions for unhealthy sleep behaviors and intentions for healthy sleep behaviors under different combinations of anthropomorphism, message framing, and voice type in cartoons. We used a three-factor between-subject experiment of two (anthropomorphism: anthropomorphic vs. non-anthropomorphic) × two (message framing: positive frame vs. negative frame) × two (voice type: cartoon child voice vs. adult female voice) design. We examined the effects of different audiovisual combinations of cartoon attitude, risk perception, and behavioral intention and the mediating role of risk perception. The research results show that (1) the integration of anthropomorphic design elements can positively impact users’ attitudes toward cartoons; (2) when the interface information is presented in a negative frame, anthropomorphism can more positively influence users’ attitudes toward cartoons than non-anthropomorphism; and (3) anthropomorphism, message framing, and voice type in cartoons significantly interact with risk perception. In addition, risk perception mediates the influence of anthropomorphism, message framing, and voice type on behavioral intention.

Implementasi Metode K-Nearest Neighbor Dalam Mengklasifikasikan Jenis Suara Berdasarkan Jangkauan Vokal

Humans have voice characteristics with different vocal ranges, namely the male voice consists of Tenor, Baritone, and Bass, while the female voice consists of Soprano, Mezzosoprano, and Alto. Determining the voice range, especially for a singer, requires a vocal trainer or musical instrument that is quite difficult to access. Therefore, a sound classification system created based on vocal range using the Harmonic Product Spectrum (HPS) feature extraction method and the K-Nearest Neighbors (KNN) classification method uses k parameters from 1 to 40. The test gets the highest accuracy on parameter k=8, which is 88.88%, so that from the resulting accuracy to prove the K-Nearest Neighbor (KNN) method gives good results in classifying the type of voice.
 Keywords: Classification, Vocal range, Harmonic Product Spectrum, K-Nearest Neighbors

Ideologies of Voice Type and Ravel's L'heure espagnole

AbstractDespite the advent of voice studies, opera scholars have yet to develop a thoroughgoing conversation about one of the most familiar elements of operatic vocal culture: voice type (categories such as soprano, tenor and the like). To address this, I suggest opera scholars analyse ideologies of voice type: the complex of ideas and practices that guide how individuals understand voice types and their relevance to the operatic experience. I devote the main part of this article to a historical case study of ideologies of voice type in action, focusing on Maurice Ravel, his 1911 opera L'heure espagnole, and the relatively obscure voice type Ravel assigned to Ramiro, the opera's male protagonist, the baryton-Martin. I argue that the characteristically modern ideology of voice type Ravel adopted in L'heure espagnole was unusual for its time and that this helps explains the work's reception.

Harmonizing Hearts with Many Voices – Analysis of Koolulam, a Mass-Singing Phenomenon, and its Contribution to Resiliency

Koolulam is a social musical initiative launched in 2017. The aim of Koolulam is to strengthen the fabric of society through mass singing - collaborative singing in large groups. This is the first study worldwide that examines this social musical phenomenon. The aim of the study to examine the profile of people who participate in Koolulam events and their motives for partaking in such an event, and to examine whether the social, communal and emotional characteristics of mass singing such as in a Koolulam event, include elements that may help strengthen the resilience of individuals in a group. This study used a mixed method approach, combining quantitative and qualitative techniques. The data were collected through questionnaires answered by 914 participants. The findings indicate that Koolulam events are perceived as a unique phenomenon, different from other multi-participant events. The shared singing experience at these events has social, communal and emotional characteristics.
 Conclusions: The study shows that singing even one song in a large group consisting of a combination of different voice types, fosters harmony and tolerance among the different voices in the group.

Detection of speech pathology based on parameters of analysis of dysphonia in speech and voice

Objective:To analysis speech pathology based on dysphonia in speech and voice（ADSV）. Methods:The acoustic signals of continuous vowels and continuous speech of one-hundred and thirteen individuals were collected, including 93 vocal cord polyps cases, 20 glottis laryngeal carcinoma cases and 47 volunteers without speech sound disorders. Cepstral peak prominence（CPP）, CPP standard deviation（CPP SD）, L/H spectral ratio（L/H ratio）, L/H ratio standard deviation（L/H ratio SD） and cepstral/spectral index of dysphonia（CSID） were analyzed by ADSV to explore the role of these parameters in the recognition of speech pathology. Results:In the acoustic signal of continuous vowels, CPP and L/H ratio in normal group were higher than those in pathological voice group（P<0.001）, while CPP SD and CSID were lower than those in pathological voice group（P<0.001）, CPP and CSID areas under ROC curve were 0.95 and 0.99, respectively, which were important acoustic parameters for diagnosing pathological voice. In continuous speech acoustic signals, CPP, CPP SD and L/H ratio in the normal group were all higher than those in the speech disorders group（P<0.001）, and the area under the curve of CPP SD was 0.90, which showed high accuracy in diagnosing pathological voice. The ADSV voice analysis parameters CPP, CPP SD, CSID, and L/H ratio also showed significant differences between the vocal cord polyp group and the glottic laryngeal cancer group. The results of the discriminant analysis model show that the use of ADSV voice parameters can distinguish vocal cord polyps and laryngeal cancers. Conclusion:The ADSV voice analysis parameters can not only distinguish the voice signals of the normal group and the pathological group, but also distinguish different types of pathological voices. It has high sensitivity and specificity in diagnosing pathological voices.

Uluslararası Müzik Sertifika Programı Teori Sınavı İçeriklerine Yönelik Öğretim Elemanı Görüşleri

Araştırmanın amacı, müzik öğretmenliği lisans programındaki müzik teorisi derslerine yönelik içeriğin, The Associated Board of the Royal Schools of Music (ABRSM)’in baraj niteliği taşıyan 5. seviye teori sınavını aşmak için yeterli olup olmadığına ilişkin öğretim elemanları görüşlerini ortaya koymaktır. Araştırma, yöntemi bakımından niteldir. Araştırmada, Batı müziği teori ve uygulaması dersini yürüten 6 öğretim elemanı ile ABRSM 5. seviye teori sınavı içeriklerine yönelik görüşmeler yapılmıştır. Görüşmeler, yapılandırılmış görüşme tekniği ile gerçekleştirilmiş; veriler içerik ana lizi ile çözümlenmiştir. Öğretim elemanlarının görüşleri doğrultusunda ders içeriğini oluşturan nota/sus işareti değerleri, aralıklar, enarmonik perde bilgisi ve ilgili tonaliteyi bulma konularının öncelikli konular olarak sıralandığı; bu konular yeterince anlaşılmadan transpoze, terimler ve işaretler, çalgı ve ses grupları konularına geçilmediği anlaşılmakla birlikte; öncelikli konular dışındaki sorularda öğretim elemanlarının farklı görüşlerde olduğu ortaya çıkmıştır.

Is Natural Necessary? Human Voice versus Synthetic Voice for Intelligent Virtual Agents

The use of intelligent virtual agents (IVA) to support humans in social contexts will depend on their social acceptability. Acceptance will be related to the human’s perception of the IVAs as well as the IVAs’ ability to respond and adapt their conversation appropriately to the human. Adaptation implies computer-generated speech (synthetic speech), such as text-to-speech (TTS). In this paper, we present the results of a study to investigate the effect of voice type (human voice vs. synthetic voice) on two aspects: (1) the IVA’s likeability and voice impression in the light of co-presence, and (2) the interaction outcome, including human–agent trust and behavior change intention. The experiment included 118 participants who interacted with either the virtual advisor with TTS or the virtual advisor with human voice to gain tips for reducing their study stress. Participants in this study found the voice of the virtual advisor with TTS to be more eerie, but they rated both agents, with recorded voice and with TTS, similarly in terms of likeability. They further showed a similar attitude towards both agents in terms of co-presence and building trust. These results challenge previous studies that favor human voice over TTS, and suggest that even if human voice is preferred, TTS can deliver equivalent benefits.

Social Determinants of Voice Outcomes: The Configurational Analysis of the Effects of LMX and Peer Relationships.

From the perspective of social relationships, this study extends the understanding of employee voice by examining voice outcomes, especially a voicer’s influence in their work team. In particular, we explore how two different social relationships, LMX and peer relationship, separately and jointly affect the ‘voice-influence’ relationship. Drawing on social network theory, we propose that higher LMX and central positions in peer networks (i.e., centrality in the friendship network) strengthen the positive impact of voice on individual influence. From a sample of 128 employees from three firms in South Korea, we found that two types of voice (promotive and prohibitive) are positively related with individual influence. This study also found that LMX strengthened the positive effect of promotive voice on a voicer’s influence. Moreover, LMX and peer relationship jointly affect the voice-influence relationship as follows: (1) a voicer with a high LMX-high centrality (in the peer network) is most influential within their team, (2) as for a low LMX-high centrality member, speaking up rather decreases individual influence. These results suggest that voice outcome is not unilateral. Rather, whose voice it is and where a voicer stands may matter more. We discussed the theoretical and practical implications of these findings in employee voice research.

Exploring the impact of leader humility on different types of voice: the role of employee other-oriented motivations

AbstractDrawing on social learning theory and taking a motivational perspective, this study mainly investigates how leader humility can promote employees' other-oriented motivations, and uncovers the other-serving motivational mechanism through which leader humility can impact their employees' different types of voice behavior. By collecting data from 152 leader–subordinate dyads through an online survey, the results revealed that leader humility was positively related to both employees' prosocial motivation and organizational concern motivation. Meanwhile, these two motivations play mediating roles in explaining how leader humility can positively affect employees' supportive voice and challenging voice. It is noteworthy that leader humility, which features highlighting the value and strength of others, is more likely to trigger employees' prosocial motivation and thus influence their voice behavior. This research extends our understanding of leader humility, employee motivation, and workplace voice. Practical implications and limitations of the results are also discussed.

Voice Recognition Security Reliability Analysis Using Deep Learning Convolutional Neural Network Algorithm

This study discusses the reliability analysis of voice recognition security using the deep learning convolutional neural network (CNN) algorithm. The CNN algorithm has learning advantages in that it is safer, faster, and more accurate. CNN also can solve user identification problems in large amounts of data. The measured voice input is ten types of user's voice with the number of iterations of 6000, 12000, and 15000 sound files. Furthermore, voice extraction features are performed to recognize conversations and retain information that is very much needed. After that, the voice file iteration data is trained to register the user's voice so that a trained model is obtained. These results measure performance (confusion matrix) to analyze the actual value compared to the predicted value in the CNN algorithm. The results obtained are that the best accuracy is obtained at 15000 sound file iterations, 96.87%, 12000 sound file iterations get 96.30%, and 6000 sound file iterations get 95.77%. CNN's performance data shows that 15000 iterations of voice files produce high accuracy. Voice recognition security helps provide high security and maintain the privacy of one's identity.

Exploring identity positionings in scholarly texts on management

Abstract Background and research aims Since scholarly texts on management have been criticised as being no longer effective in communicating today's changing sociocultural, disciplinary, and practical contexts, my purpose in this paper is to conceptualise the identity options management authors can assume to communicate disciplinary knowledge and beliefs. Theoretical perspective The theoretical perspectives involved in this analysis include selected aspects of Harré and van Langenhove's (1999) positioning theory that I linked with my model of writer identity as a trichotomy of selves (individual self, collective self, depersonalised self), textually conveyed in the three types of voice (Lehman, 2018; Lehman and Sułkowski, 2020). Key findings Based on this conceptual framework, specific advice is provided as to how academics can create a reader-inclusive or authoritative writer persona in their texts. In doing so, I support the recent efforts in Critical Management Studies (CMS) to ‘write differently’ in order to address the aesthetic, moral, and political concerns of writing in the field.

A narrative review of psychological theories of post-traumatic stress disorder, voice hearing, and other psychotic symptoms.

Most voice hearers report childhood trauma. Many voice hearers report comorbid post-traumatic stress symptoms and that the content of their voices (auditory verbal hallucinations) is directly (voices repeat phrases spoken by perpetrators) or indirectly (voice content and trauma is thematically similar) related to their trauma. The factors that maintain trauma-related voices are unknown, and there is limited research in this area. This study aimed to identify potential maintaining factors of trauma-related voices by reviewing models of post-traumatic stress disorder (PTSD) and positive symptoms of psychosis. Models of PTSD and positive symptoms were reviewed to identify potential factors that are unique and common to both sets of symptoms. We reviewed 10 models of PTSD, 4 models of positive symptoms, and 2 trauma-informed models of voice hearing. One model provided a theoretical explanation of different types of trauma-related voices. Twenty-one factors were extracted from 16 theoretical models. No existing model incorporated all these factors. Existing PTSD and positive symptom models present a range of common and unique factors. There may be value in extending existing integrative models to include a broader range of potential factors that could explain different pathways to, and expressions of, trauma-related voices. A future research agenda is presented to investigate how such an extension could lead to more complete individualized case formulations and targeted treatments.

‘Doing’ digital transformation: theorising the practitioner voice

ABSTRACT The objective of this theory-building research is to explore the defining characteristics of ‘doing’ Digital Transformation (DT) and present a holistic account of the practitioner practices that characterise ‘doing’ DT. For the purposes of this research ‘doing’ DT is defined as leveraging digital technologies to significantly alter an organisational design in order to enhance customer engagement. To fulfil this objective, we select 16 key informants (digital transformation leaders) based on their organisational perspective (Business or IT) and role (Strategic or Operational), which facilitates hearing 4 types of practitioner voices. Following an inductive open coding approach, 348 excerpts were coded, leading to the emergence of 95 concepts, which were further grouped into 14 categories. In this paper, we focus our write-up on the six most frequently occurring categories that are shaped by all four key informant groups (practitioner voices). This paper is unique in providing a holistic categorisation of the defining characteristics of ‘doing’ DT, while also providing 24 ‘Practitioner Priorities’. These ‘Practitioner Priorities’ sharpens the focus of academia and practice, highlighting the ‘role of people’, ‘role of data’ and ‘role of technology’ when ‘doing’ DT.