Building personalised synthetic voices for individuals with severe speech impairment

Creer, Sarah; Cunningham, Stuart; Green, Phil; Yamagishi, Junichi

doi:10.1016/j.csl.2012.10.001

Cited by 20 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to recent books, 12 literature reviews 13–22 and research articles, 23–34 the Parkinson's disease identification can be broadly classified into various motor and non‐motor symptoms as shown in Figures 1 and 2 respectively.…”

Section: Related Workmentioning

confidence: 99%

Cloud‐assisted Parkinson disease identification system for remote patient monitoring and diagnosis in the smart healthcare applications

Harimoorthy

Thangavelu²

2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary The development of a cloud‐based Parkinson's disease identification system is identified as one of the most challenging issues for predictive telediagnosis and telemonitoring in the emerging smart healthcare applications. The traditional way of Parkinson's disease identification by clinical parameters is more costly and uncomfortable for rural people to avail the testing and diagnosis from the remote place. So, the cloud‐assisted Parkinson's disease identification system (CAPDIS) is proposed based on non‐clinical parameters with patient‐centric and cost‐effective features for helping the poor patients living in rural as well as urban areas. In addition, the proposed system diagnoses the remote patient by examining the symptoms like dysphonia which is identified as the most severe neurodegenerative disorder in the world. Further, the proposed system has experimented with the benchmark voice dataset collected from the University of California‐Irvine (UCI) repository. It shows that the proposed CAPDIS system with adaptive linear kernel support vector machines (k‐SVM) classifier has significant improvements on detection accuracy, specificity, sensitivity, and Matthews's correlation coefficient scores while comparing to the existing classifiers. Therefore, the proposed adaptive linear k‐SVM classifiers provide 10% improvements on prediction accuracy and F1‐Score over the existing polynomial, radial basis, and sigmoidal‐based k‐SVM classifiers.

show abstract

Section: Related Workmentioning

confidence: 99%

Cloud‐assisted Parkinson disease identification system for remote patient monitoring and diagnosis in the smart healthcare applications

Harimoorthy

Thangavelu²

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…This is unsatisfactory given the evidence that without the full embodiment of emotional expression present in interpersonal interactions, communication, coordination and performance can suffer immensely ( Gerdes et al, 2014 ). Other applications of expressive speech are covered elsewhere in this review, but for further examples of areas of application which appear promising at this stage, we direct the reader to consider narratives in gaming arenas, voice conversion for the purposes of, and the use of human–human interaction analyses to aid our understanding of social dynamics ( Burkhardt and Stegmann, 2009 ; Schröder, 2009 ; Vinciarelli et al, 2009 ; Devillers and Campbell, 2011 ; Creer et al, 2013 ; Esposito et al, 2015 ).…”

Section: When Is Artificial Emotional Prosody Beneficial For Users?mentioning

confidence: 99%

“…HCI-AI that express emotion cues could especially enhance the ability to make sense of and communicate with others in people with difficulty understanding, communicating and regulating their emotion systems, such as autism, and the affective disorders ( Robinson and el Kaliouby, 2009 ). Personalized voices may also be possible for those who rely on alternative or augmented communication devices, by mapping existing text to speech corpora onto a voice personalized to the residual vocal characteristics of a specific user ( Creer et al, 2013 ; Mills et al, 2014 ). Whilst future assistive HCI-AI agents with emotional prosody might be expected to benefit users of all ages, the development of socially intelligent assistive technology has promise for increasing quality of life for older adults in particular, in the form of reminder systems, telecommunication systems, surveillance systems, and the ability to provide social interaction and complete daily household tasks ( Beer et al, 2015 ).…”

Section: What About the Future?mentioning

confidence: 99%

What is the Value of Embedding Artificial Emotional Prosody in Human–Computer Interactions? Implications for Theory and Design in Psychological Science

Mitchell

2015

Front. Psychol.

View full text Add to dashboard Cite

In computerized technology, artificial speech is becoming increasingly important, and is already used in ATMs, online gaming and healthcare contexts. However, today’s artificial speech typically sounds monotonous, a main reason for this being the lack of meaningful prosody. One particularly important function of prosody is to convey different emotions. This is because successful encoding and decoding of emotions is vital for effective social cognition, which is increasingly recognized in human–computer interaction contexts. Current attempts to artificially synthesize emotional prosody are much improved relative to early attempts, but there remains much work to be done due to methodological problems, lack of agreed acoustic correlates, and lack of theoretical grounding. If the addition of synthetic emotional prosody is not of sufficient quality, it may risk alienating users instead of enhancing their experience. So the value of embedding emotion cues in artificial speech may ultimately depend on the quality of the synthetic emotional prosody. However, early evidence on reactions to synthesized non-verbal cues in the facial modality bodes well. Attempts to implement the recognition of emotional prosody into artificial applications and interfaces have perhaps been met with greater success, but the ultimate test of synthetic emotional prosody will be to critically compare how people react to synthetic emotional prosody vs. natural emotional prosody, at the behavioral, socio-cognitive and neural levels.

show abstract

“…Incorporating information about ethnolinguistic variation may be especially vital for researchers working in the area of speech synthesis. Individuals with medical conditions that impact their speech frequently rely on systems like Speech Generating Devices (SGD), and patients show strong preferences for systems that generate voices that align with their social identities (Crabtree et al, 1990;Creer et al, 2013). To date, few existing systems take into account factors such as ethnolinguistic variation, but having a naturalistic voice output system has been shown to improve the quality of life for patients with these types of conditions (Creer et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Perception in Black and White: Effects of Intonational Variables and Filtering Conditions on Sociolinguistic Judgments With Implications for ASR

Holliday

2021

Front. Artif. Intell.

View full text Add to dashboard Cite

This study tests the effects of intonational contours and filtering conditions on listener judgments of ethnicity to arrive at a more comprehensive understanding on how prosody influences these judgments, with implications for austomatic speech recognition systems as well as speech synthesis. In a perceptual experiment, 40 American English listeners heard phrase-long clips which were controlled for pitch accent type and focus marking. Each clip contained either two H* (high) or two L+H* (low high) pitch accents and a L-L% (falling) boundary tone, and had also previously been labelled for broad or narrow focus. Listeners rated clips in two tasks, one with unmodified stimuli and one with stimuli lowpass filtered at 400 Hz, and were asked to judge whether the speaker was “Black” or “White”. In the filtered condition, tokens with the L+H* pitch accent were more likely to be rated as “Black”, with an interaction such that broad focus enhanced this pattern, supporting earlier findings that listeners may perceive African American Language as having more variation in possible pitch accent meanings. In the unfiltered condition, tokens with the L+H* pitch accent were less likely to be rated as Black, with no effect of focus, likely due to the fact that listeners relied more heavily on available segmental information in this condition. These results enhance our understanding of cues listeners rely on in making social judgments about speakers, especially in ethnic identification and linguistic profiling, by highlighting perceptual differences due to listening environment as well as predicted meaning of specific intonational contours. They also contribute to our understanding of the role of how human listeners interpret meaning within a holistic context, which has implications for the construction of computational systems designed to replicate the properties of natural language. In particular, they have important applicability to speech synthesis and speech recognition programs, which are often limited in their capacities due to the fact that they do not make such holistic sociolinguistic considerations of the meanings of input or output speech.

show abstract

Building personalised synthetic voices for individuals with severe speech impairment

Cited by 20 publications

References 24 publications

Cloud‐assisted Parkinson disease identification system for remote patient monitoring and diagnosis in the smart healthcare applications

Cloud‐assisted Parkinson disease identification system for remote patient monitoring and diagnosis in the smart healthcare applications

What is the Value of Embedding Artificial Emotional Prosody in Human–Computer Interactions? Implications for Theory and Design in Psychological Science

Perception in Black and White: Effects of Intonational Variables and Filtering Conditions on Sociolinguistic Judgments With Implications for ASR

Contact Info

Product

Resources

About