Voice Type Research Articles

Under-Represented Speech Dataset from Open Data: Case Study on the Romanian Language

This paper introduces the USPDATRO dataset. This is a speech dataset, in the Romanian language, constructed from open data, focusing on under-represented voice types (children, young and old people, and female voices). The paper covers the methodology behind the dataset construction, specific details regarding the dataset, and evaluation of existing Romanian Automatic Speech Recognition (ASR) systems, with different architectures. Results indicate that more under-represented speech content is needed in the training of ASR systems. Our approach can be extended to other low-resourced languages, as long as open data are available.

Voice Type Component Profile Model of Glottal Gap Voice in Ex Vivo Canine Larynges

This paper aimed to create a voice type component profile (VTCP) to model a glottal gap during phonation. VTCP was generated from phonation from eight excised canine larynges with induced posterior glottal gaps. Glottal gaps were induced using metal shims with widths ranging from 0.5 to 3.5mm, in 0.5 mm increments. Acoustic data was collected under each gap condition, and a custom MATLAB software was used to analyze the data for VTCP. The trends of each VTC were analyzed with changes in glottal gap size. Increasing glottal gap led to a decrease in VTC1 and an increase in VTC4. Post-Hoc Tukey tests found that for both VTC4 and VTC1, The 1.5mm group differed from the 2, 2.5, and 3.5mm group. Additionally, in both VTC1 and VTC4 there was a significant difference between both the control and 0.5mm shim groups and the 2, 2.5, 3, and 3.5mm shim groups. VTC2 followed a similar trend as VTC1. Average VTC3 was highest at control, and the 1, 2, 2.5, 3, and 3.5mm shim groups significantly differed from the control group. Kendall correlation tests showed that there was a significant weak inverse relationship with glottal gap size and VTC1, VTC2, and VTC3 and a significant weak positive correlational relationship with glottal gap size and VTC4. As glottal gap width increased, phonation exhibited increased turbulence associated with increased breathiness. Periodicity decreased as turbulence increased. Increased turbulence was shown to be derived from the glottal level. The size of the induced glottal gap was the cause of the turbulent signals. The study highlights the potential of VTCP analysis in detecting subtle changes in glottal closure and suggests avenues for further research in diagnosing voice disorders.

The plurivocal university: Typologizing the diverse voices of a research university on social media.

Science communication has diversified in the wake of the digital transformation of communication and media ecosystems. Social media enable universities, but also academics and institutions affiliated with them, to expand their communication. This leads to increasing plurivocality of universities, yet the many different voices remain largely unexplored. This study develops a typology to conceptually distinguish eight voices by their representational role, hierarchical embeddedness, type, and affiliation. Based on a quantitative content and social network analysis of more than 600 Twitter accounts linked to a research university, it identifies six types of voices empirically. The study compares interactions among these voices, showing differences between central and decentral, as well as institutional and individual voices, and highlighting closer exchanges between voices within the same disciplinary communities. It also examines topics and tonality, revealing that decentral institutional voices engage most in science-related topics, and that only current and former students express critical views.

Accuracy of Automatic Processing of Speech-Language Pathologist and Child Talk During School-Based Therapy Sessions.

This study examines the accuracy of Interaction Detection in Early Childhood Settings (IDEAS), a program that automatically transcribes audio files and estimates linguistic units relevant to speech-language therapy, including part-of-speech units that represent features of language complexity, such as adjectives and coordinating conjunctions. Forty-five video-recorded speech-language therapy sessions involving 27 speech-language pathologists (SLPs) and 56 children were used. The F measure determines the accuracy of IDEAS diarization (i.e., speech segmentation and speaker classification). Two additional evaluation metrics, namely, median absolute relative error and correlation, indicate the accuracy of IDEAS for the estimation of linguistic units as compared with two conditions, namely, Oracle (manual diarization) and Voice Type Classifier (existing diarizer with acceptable accuracy). The high F measure for SLP talk data suggests high accuracy of IDEAS diarization for SLP talk but less so for child talk. These differences are reflected in the accuracy of IDEAS linguistic unit estimates. IDEAS median absolute relative error and correlation values for nine of the 10 SLP linguistic unit estimates meet the accuracy criteria, but none of the child linguistic unit estimates meet these criteria. The type of linguistic units also affects IDEAS accuracy. IDEAS was tailored to educational settings to automatically convert audio recordings into text and to provide linguistic unit estimates in speech-language therapy sessions and classroom settings. Although not perfect, IDEAS is reliable in automatically capturing and returning linguistic units, especially in SLP talk, that are relevant in research and practice. The tool offers a way to automatically measure SLP talk in clinical settings, which will support research seeking to understand how SLP talk influences children's language growth.

A Critical Discourse Analysis of Active and Passive Voice in Three News Texts

This paper applies CDA (critical discourse analysis) to display the hidden relationship between language and power in the discourse of the media; it focuses on the issues which are related to the use of passive or active voice, and tries to investigate which forms of voice are used (passive or active). Data have been collected from three different news texts on the subject of Iraq War Logs. The data have been analysed by using the framework model of Fowler et al. [6] and the findings have been discussed within the framework which is provided by Fairclough, N. [4]. The results show that there is a hidden relationship between language and power in the discourse of the media. Access to the media discourse is limited to specific people only, while other people lack this access. Moreover, the types of voice (passive or active) that are used in different texts determine which sentences are more powerful.

The voice quality of pedagogical agent impacts learning and agent perceptions

AbstractBackgroundThe voices virtual on‐screen characters use has been shown to impact learning and perception outcomes. Recent replication research on these voices showed that synthetic voices were not a detriment if produced by a high‐quality engine with clear articulation. The current manuscript examines previous accent research that utilized now outdated engines, to determine if the impact of accents still holds with high‐quality engines and voice actors.ObjectivesTo investigate the impact on learning and perceptions with pedagogical agents speaking in accented voices, synthetic voices, and the interaction between the two using modern voice engines.MethodsThis study is a between‐subjects two (accent) by two (type) factorial design to determine the impact the voice accent, voice type, and the interaction have on learning retention, learning transfer, mental effort efficiency, and perception measures. 197 participants were recruited from the online Amazon's Mechanical Turk with qualifications of 18 years of age, “normal or corrected‐to‐normal hearing”, and located with the continental United States of America.Results and ConclusionsThere were no significant differences between the accented conditions or interaction effects, deviating from previous research that showed impact of accents on learning. The synthetic condition had significantly lower knowledge retention, knowledge transfer, mental effort efficiency, and perception measures than the human professional. These findings demonstrate the importance of considering voice quality when designing pedagogical agents. Previous research showed synthetic voices perform as well as the average voice, and this research continues the narrative of voice quality by showing professional recordings outperform modern synthetic engines.

A lecturer’s voice quality and its effect on memory, listening effort, and perception in a VR environment

Many lecturers develop voice problems, such as hoarseness. Nevertheless, research on how voice quality influences listeners’ perception, comprehension, and retention of spoken language is limited to a small number of audio-only experiments. We aimed to address this gap by using audio-visual virtual reality (VR) to investigate the impact of a lecturer’s hoarseness on university students’ heard text recall, listening effort, and listening impression. Fifty participants were immersed in a virtual seminar room, where they engaged in a Dual-Task Paradigm. They listened to narratives presented by a virtual female professor, who spoke in either a typical or hoarse voice. Simultaneously, participants performed a secondary task. Results revealed significantly prolonged secondary-task response times with the hoarse voice compared to the typical voice, indicating increased listening effort. Subjectively, participants rated the hoarse voice as more annoying, effortful to listen to, and impeding for their cognitive performance. No effect of voice quality was found on heard text recall, suggesting that, while hoarseness may compromise certain aspects of spoken language processing, this might not necessarily result in reduced information retention. In summary, our findings underscore the importance of promoting vocal health among lecturers, which may contribute to enhanced listening conditions in learning spaces.

Social Undermining and Promotive Voice: The Moderating Effects of Procedural Justice.

Organizations are increasingly depending on their employees to contribute suggestions aimed at enhancing organizational processes, boosting overall efficiency, and fostering innovation. However, some factors might hinder employees from expressing their thoughts. While there is evidence suggesting an effect of supervisor social undermining behavior on employee voice, the impact on innovative types of voice, specifically promotive voice, remains uncertain. This study aims to explore the association between supervisor social undermining and employee promotive voice. Moreover, this research investigates how employee perceptions of procedural justice moderate this relationship, utilizing the Conservation of Resources theory. Data were collected from 115 highly skilled employees, and hierarchical regression analysis was employed to assess the proposed hypotheses. The findings suggest that when individuals encounter social undermining behavior from their supervisor, they are less inclined to engage in promotive voice behavior. Interestingly, the results indicate that this relationship becomes stronger when individuals possess higher perceptions of procedural justice. To the best of our knowledge, this study is the first to investigate the impact of supervisor social undermining on promotive voice while considering procedural justice as a moderator in this relationship. The findings of this study suggest several theoretical and practical implications and provide directions for future research.

"Lombard Effect" and Voice Changes in Adductor Laryngeal Dystonia: A Pilot Study.

The aim was to describe the acoustic, auditory-perceptive, and subjective voice changes under the Lombard effect (LE) in adductor laryngeal dystonia (AdLD) patients. Subjective perception of vocal effort (OMNI Vocal Effort Scale OMNI-VES), Maximum Phonation Time (MPT), and the perceptual severity of dysphonia (GRBAS scale) were assessed in condition of stillness and under LE in 10 AdLD patients and in 10 patients with typical voice. Speakers were asked to produce the sustained vowel /a/ and to read a phonetically balanced text aloud. Using the PRAAT software, the following acoustic parameters were analyzed: Mean Pitch (Hz), Minimum and Maximum Intensity (dB), the Fraction of Locally Unvoiced Frames, the Number of Voice Breaks, the Degree of Voice Breaks (%), the Cepstral Peak Prominence-Smoothed (CPPS) (dB). Under LE, the AdLD group showed a decrease of both G and S parameters of GRBAS and subjective effort, mean MPT increased significantly; in the controls there were no significant changes. In both groups under LE, pitch and intensity of the sustained vowel /a/ significantly increased consistently with LE. In the AdLD group the mean gain of OMNI-VES score and the mean gain of each parameter of the speech analysis were significantly greater than the controls' ones. Auditory feedback deprivation obtained under LE improves subjective, perceptual-auditory, and acoustics parameters of AdLD patients. These findings encourage further research to provide new knowledge into the role of the auditory system in the pathogenesis of AdLD and to develop new therapeutic strategies. 4 Laryngoscope, 134:3754-3760, 2024.

Relative Fundamental Frequency in Individuals with Globus Syndrome and Muscle Tension Dysphagia.

Relative fundamental frequency (RFF) has been investigated as an acoustic measure to assess for changes in laryngeal tension. This study aimed to assess RFF in individuals with globus syndrome, individuals with muscle tension dysphagia (MTDg), and individuals with typical voices. RFF values were calculated from the speech acoustics of individuals with globus syndrome (n=12), individuals with MTDg (n=12), and age- and sex-matched controls with typical voices (n=24). An analysis of variance was performed on RFF values to assess the effect of group. There was no statistically significant effect of group on RFF values, with similar values for individuals with globus syndrome, individuals with MTDg, and control participants. These results suggest that individuals with these disorders do not appear to possess paralaryngeal muscle tension in a locus and/or manner that directly impacts voice production.

Deviation from typical organic voices best explains a vocal uncanny valley

The uncanny valley describes the negative evaluation of near humanlike artificial entities. Previous research with synthetic and real voices failed to find an uncanny valley of voices. This may have been due to an incomplete selection of stimuli. In Experiment 1 (n = 50), synthetic, normal, and deviating voices (distorted and pathological) were rated on uncanniness and human likeness and categorized as human or non-human. Results showed a non-monotonic function when the uncanniness was plotted against human likeness indicative of an uncanny valley. However, the shape could be divided into two monotonic functions based on voice type (synthetic vs deviating). Categorization ambiguity could not predict voice uncanniness but moderated the effect of realism on uncanniness. Experiment 2 (n = 35) found that perceived organicness, animacy, and mind attribution of voices significantly moderated the effect of realism on uncanniness. Results indicate a vocal uncanny valley driven by deviations from typical human voices. While voices can fall into an uncanny valley, synthetic voices successfully escape it. Finally, the results support the account that uncanniness is caused by deviations from familiar categories, rather than categorical ambiguity or the misattribution of mind or animacy.

Music Reviews

Abstract: This column includes reviews of a four-volume opera anthology series organized by voice type (soprano, mezzo, tenor and baritone), by American composer Jake Heggie. Also reviewed are art song settings of the poetry of Harlem Renaissance poet Langston Hughes: "Dream Variations" by American composer Mark Carlson, and "Three Dream Portraits and Three Original Songs" by Margaret Bonds; the latter appears in an edition by scholar Louise Toppin.

Group ethical voice and ethical behaviors: The mediating role of group moral transitive motivation and moderating role of group faultlines

AbstractEthical voice involves individuals’ perceptions of what is right and what is wrong. Although prior research has investigated the impacts of individual‐level prohibitive ethical expression on personal outcomes, there has been limited examination of ethical voice at the group level. Our study examines how and when different types of ethical voice influence group outcomes. Using data gathered from 363 participants from 61 groups in two Chinese companies, the results reveal that promotive and prohibitive ethical voices at the group level exert opposing influences on group moral transitive motivation. Group moral transitive motivation serves as a mediating factor in the association between the two types of ethical voice and group ethical behaviors (GEB). In addition, group faultlines moderate the impact of promotive ethical voice and prohibitive ethical voice on group moral transitive motivation and on GEB (via group moral transitive motivation). Our study extends the focus of research from a single type of ethical voice at the individual level to multiple types at the group level. The findings contribute to the body of knowledge regarding group ethical voice (GEV) by articulating its mediating mechanism as well as its boundary condition. This research provides valuable insights for researchers and managers by offering a comprehensive understanding about the role of different types of GEV and how to reform GEV.

SVCGAN: Speaker Voice Conversion Generative Adversarial Network for Children’s Speech Conversion and Recognition

Automatic speech recognition (ASR) refers to a technological process that entails the conversion of spoken language into written text. However, the acoustic distinctions between children’s speech and adult speech are substantial, rendering the automatic speech recognition system trained on adult speech inadequate for effectively recognizing children’s speech. To overcome this issue, in this study, we propose speaker conversion generative adversarial network (SVCGAN). SVCGAN is a novel non-parallel voice conversion model, which enhances three key areas: log-cosh loss, semantic-similarity loss, and third adversarial loss. Therefore, the incorporation of these losses better protects semantic information for young children during voice conversion process and improves the quality of the converted speech. Additionally, the character error rate (CER) of children’s speech recognition can benefit from children’s speech transformed into adult speech. Experimental results suggest that SVCGAN demonstrates superior performance across multiple dimensions compared to both CycleGAN-VC3 and MaskCycleGAN-VC models. It encompasses training efficiency, semantic information similarity, voice type similarity, sound naturalness and intelligibility, which leads to a reduction in the CER of speech recognition for young children.

A case of transdisciplinarity and collaborative decision making: the co-construction of Gendered Food Product Profiles.

Crop breeding in sub-Saharan Africa has made considerable gains; however, postharvest and food-related preferences have been overlooked, in addition to how these preferences vary by gender, social difference and context. This context is changing as participatory approaches using intersectional gender and place-based methods are beginning to inform how breeding programmes make decisions. This article presents an innovative methodology to inclusively and democratically prioritise food quality traits of root, tuber and banana crops based on engagement with food systems actors and transdisciplinary collaboration. The outcome of the methodology is the Gendered Food Product Profile (GFPP) - a list of prioritised food quality characteristics - to support breeders to make more socially inclusive decisions on the methods for trait characterisation to select genotypes closer to the needs of food system actors. This article reviews application of the methodology in 14 GFPPs, presents illustrative case studies and lessons learned. Key lessons are that the transdisciplinary structure and the key role of social scientists helped avoid reductionism, supported co-learning, and the creation of GFPPs that represented the diverse interests of food system actors, particularly women, in situ. The method partially addressed power dynamics in multidisciplinary decision making; however, effectiveness was dependent on equitable team relations and supportive institutions committed to valuing plural forms of knowledge. Actions to address power asymmetries that privilege particular types of knowledge and voices in decision making are crucial in techno-science projects, along with opportunities for co-learning and long-term collaboration and a transdisciplinary structure at higher level. © 2024 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

»Vi ser att [eleven] har behov av särskilt stöd» Om kunskapsbildning och informationshantering i skolans elevutredningar

This study engages with the discursive construction of knowledge in school documents concerning pupils in need of special pedagogical support. In these texts, information from various voices is represented and recontextualized, meaning that images of pupils are negotiated and outlined, and ultimately knowledge about pupils and their learning is constructed discursively. The aim of the study is to investigate practices of knowledge construction in these texts. The data consist of 27 documents written by teachers who teach in lower secondary school (7th–9th grades). Drawing on linguistic discourse analysis, lexico-grammatical features are analyzed from both a qualitative and a quantitative perspective. The study shows how information originating from various voices is managed and framed by linguistic means in qualitatively different ways, and how the framing of information contributes to construction of several kinds of knowledge. In the analysis, five forms of framing are identified, along with six different types of voices. By quantifying the forms of framing as related to various voices, the study maps out the legitimization and delegitimization of various voices via the construction of different kinds of knowledge. Even though information from several voices is represented in the texts, it is primarily information from either the writer him/herself or written sources, such as previous documentation about pupils, that is legitimized by the writer.

Contemporary Vocal Repertoire Considerations for the Classical Singer

Abstract: Author Justin John Moniz addresses the exploration of contemporary vocal repertoire for the classical singer. Moniz discusses effective teaching methods rooted in evidence-based practice and advocates for the exploration of student curiosities outside one’s primary area of concentration. Included is a sample list of popular song repertoire for four voice types: soprano, mezzo-soprano, tenor, and baritone. These selections are intended to provide even those most unfamiliar with popular song an opportunity to explore a new style with greater probabilities of ease and coordination.

Gender-expansive listeners invite us to reconsider voice categorization as a simple matter of pitch and timbre

Past literature has focused on pitch and timbre cues as the main determinants of the voice of an actor (a speaker or a singer). But in real life, judges rely on non-auditory cues such as the actor’s facial features, height, body size and shape. Resisting these visual biases could provide more accurate assessment of a voice but requires a stronger dissociation between auditory attributes and physical appearance, an ability hypothetically acquired by gender-expansive participants. In three online studies, we examine Faching (allocating voices into traditional categories). In study 1, 166 participants (85 cis, 81 gender-expansive) rated 144 audio (A) samples from 18 different actors (3 from each major Fach category, excluding countertenor) along a slider labeled low/dark to high/bright. Participants then guessed the voice types of the same actors in silent videos (V), before rating them in AV combinations. The cis group exhibited 30% more visual bias than the gender-expansive group. To further understand how gender-expansive participants obtain this benefit, we manipulated the fundamental frequency (in study 2) or the vocal tract length (in study 3) by ± 3 semitones from the original stimuli. Preliminary findings suggest that the two groups differ in the face of timbre but not pitch manipulations.

Shy One: The Songs of Rebecca Clarke

Abstract: Rebecca Clarke, 1886–1979, was a trailblazing British violist and composer. She was one of the first women to play in a professional symphony orchestra, and her compositions were exemplary, even though the press in her lifetime doubted they were written by a woman. This article provides a detailed biography of Clarke’s life, an overview of her general compositional style, pedagogical considerations for singing her music, and a closer look at eight of her strongest songs. For each song, a synopsis of the poem and musical analysis is presented, as well as details about range, tessitura, song length and suggested voice type.

The effects of vowel, pitch, and dynamics on the emotional characteristics of the Mezzo-Soprano, Countertenor, and Baritone Voices

Previous research on the soprano, alto, tenor, and bass voices have shown that their emotional characteristics change with different vowel, pitch, and dynamics. This work continues the investigation with the mezzo-soprano, countertenor, and baritone voices. Listening tests were conducted whereby listeners gave absolute judgements on the 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 Comic had an upward trend across the pitch range, whereas Calm, Mysterious, Shy, and Sad had a downward trend. Angry and Scary had different trends among the voices. For most categories, all five vowels were mostly similar in terms of emotional expressiveness, with exceptional cases for the baritone voice. Overall, pitch had the strongest effect and was almost twice as strong as dynamics and vowel, with dynamics slightly stronger than vowel. Vowel O had the largest strength-of-expressiveness overall, closely followed by vowels U and A, and finally vowels I and E last. These results give a quantified preliminary perspective on how vowel, pitch, and dynamics shape emotional expression in the voices across a wide range of voice types.