Does Gender and Accent of Voice Matter?

Mubarak, Eman; Shahid, Tooba; Mustafa, Maryam; Naseem, Mustafa

doi:10.1145/3392561.3397588

Cited by 5 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparable study using automated voice calls found that female participants preferred a female voice to a male voice 8. Another study that investigated the impact of voice characteristics on trust in low-literacy, low-income audiences within a patriarchal context found that the gender or accent of the voice influenced the trust in the information presented, with male participants finding male voice recordings to be more credible than female recordings 40. This finding can guide the design of future remote engagement strategies through mobile phones, particularly in patriarchal societies.…”

Section: Discussionmentioning

confidence: 99%

Understanding rural women's preferences for telephone call engagement with primary health care providers in Nigeria: a discrete choice experiment

Umar,

Hill,

Schellenberg

et al. 2023

BMJ Glob Health

View full text Add to dashboard Cite

BackgroundThe COVID-19 pandemic has accelerated the use of mobile phones to provide primary health care services and maintain continuity of care. This study aims to understand rural women’s preferences for telephone call engagement with primary health care providers in Nigeria.MethodsA discrete choice experiment was conducted alongside an action research project that empowered primary health care workers to develop and implement a telephone call intervention to assess and enhance experiences with facility childbirth care. Between January and March 2022, 30 providers from 10 primary health care facilities implemented the choice experiment among rural women who had institutional childbirth to elicit service user preferences for telephone call engagement. The women were asked to express their preferred scenario for telephone call engagement with their primary health care providers. Generalised linear mixed models were used to estimate women’s preferences.ResultsData for 460 women were available for the discrete choice experiment. The study showed that rural women have preferences for telephone call engagement with primary health care providers. Specifically, women preferred engaging with female to male callers (β=1.665 (95% CI 1.41, 1.93), SE=0.13, p<0.001), preferred call duration under 15 min (β=1.287 (95% CI 0.61, 1.96), SE=0.34, p<0.001) and preferred being notified before the telephone engagement (warm calling) (β=1.828 (95% CI 1.10, 2.56), SE=0.37, p<0.001). Phone credit incentive was also a statistically significant predictor of women’s preferences for engagement. However, neither the availability of scheduling options, the period of the day or the day of the week predicts women’s preferences.ConclusionsThe study highlights the importance of understanding rural women’s preferences for telephone call engagement with healthcare providers in low-income and middle-income countries. These findings can inform the development of mobile phone-based interventions and improve acceptability and broader adoption.

show abstract

Section: Discussionmentioning

confidence: 99%

Understanding rural women's preferences for telephone call engagement with primary health care providers in Nigeria: a discrete choice experiment

Umar,

Hill,

Schellenberg

et al. 2023

BMJ Glob Health

View full text Add to dashboard Cite

show abstract

Towards a Positive Thinking About Deepfakes: Evaluating the Experience of Deepfake Voices in the Emotional and Rational Scenarios

Chang,

Chien

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Age group classification and gender recognition from speech with temporal convolutional neural networks

Sánchez-Hevia

Gil-Pita

Rosa-Zurera

2022

Multimed Tools Appl

View full text Add to dashboard Cite

This paper analyses the performance of different types of Deep Neural Networks to jointly estimate age and identify gender from speech, to be applied in Interactive Voice Response systems available in call centres. Deep Neural Networks are used, because they have recently demonstrated discriminative and representation capabilities in a wide range of applications, including speech processing problems based on feature extraction and selection. Networks with different sizes are analysed to obtain information on how performance depends on the network architecture and the number of free parameters. The speech corpus used for the experiments is Mozilla’s Common Voice dataset, an open and crowdsourced speech corpus. The results are really good for gender classification, independently of the type of neural network, but improve with the network size. Regarding the classification by age groups, the combination of convolutional neural networks and temporal neural networks seems to be the best option among the analysed, and again, the larger the size of the network, the better the results. The results are promising for use in IVR systems, with the best systems achieving a gender identification error of less than 2% and a classification error by age group of less than 20%.

show abstract

Does Gender and Accent of Voice Matter?

Cited by 5 publications

References 15 publications

Understanding rural women's preferences for telephone call engagement with primary health care providers in Nigeria: a discrete choice experiment

Understanding rural women's preferences for telephone call engagement with primary health care providers in Nigeria: a discrete choice experiment

Towards a Positive Thinking About Deepfakes: Evaluating the Experience of Deepfake Voices in the Emotional and Rational Scenarios

Age group classification and gender recognition from speech with temporal convolutional neural networks

Contact Info

Product

Resources

About