The impact of participation in research for speech and language therapy departments and their patients: A case example of the Big CACTUS multicentre trial of self-managed computerized aphasia therapy.

BACKGROUND: In order to conduct research that is meaningful to speech and language therapy services and their patients, it is often desirable to conduct the research within routine clinical services. This can require considerable time and commitment from speech and language therapists (SLTs). It is therefore important to understand the impact that such participation in research can have. AIMS: To explore the impact of research participation in the Big CACTUS study of self-managed computerized aphasia therapy conducted in 21 UK NHS speech and language therapy departments. METHODS & PROCEDURES: An online survey was sent to SLTs who took the lead role for the study at their NHS Trust to evaluate the impact of study participation in three domains: capacity-building, research development and health services. The questionnaire, based on the VICTOR framework for evaluating research impact, included Likert scale statements and closed and open-ended questions. The results from open-ended questions were coded and analysed using framework analysis in NVivo 12 and the data from closed questions were analysed descriptively. OUTCOMES & RESULTS: A total of 12 SLTs returned the survey. Nine codes were identified from open-ended questions and 20 predefined from the literature. Analysis of the responses demonstrated the perceived impact including improvements in practices and access to therapy, investments in infrastructure, increased SLT profile, and impact on research culture among SLTs. The usefulness of the intervention during the COVID-19 pandemic was also highlighted. CONCLUSIONS & IMPLICATIONS: The results suggest participation in Big CACTUS has resulted in improvements in patient care and SLT research capacity and culture in speech and language therapy departments. WHAT THIS PAPER ADDS: What is already known on the subject Practice-based research is encouraged to assist with the clinical relevance of the research findings. Participation in research can be seen as an activity that is additional to the core business of patient care and it can be difficult to secure time to participate or conduct research in clinical settings. Impact evaluation initiatives of individual trials facilitate early identification of benefits beyond the trial. What this paper adds to existing knowledge This study describes specific examples of the impact on services, staff and patients from SLT participation and leadership in the Big CACTUS speech and language therapy trial in clinical settings. What are the potential or actual clinical implications of this study? Clinical services participating in research may benefit from improved clinical care for patients both during and after the study, an improved professional reputation, and increased research capacity and culture within the clinical settings.

Impact of COVID-19 in relation to the outpatient pediatric feeding therapy experience: A speech-language pathologist's review of literature and professional experience.

It is well known in the medical and pediatric feeding community how parental stress affects outcomes of pediatric nutrition and feeding behaviors. There is growing literature suggesting the impact of the COVID-19 pandemic in relation to caregiver and child stress. It could be suggested that this increase in stress contributed to or exacerbated pediatric feeding difficulties. In addition, the COVID-19 pandemic resulted in pediatric rehabilitation therapists quickly transitioning from in-person to virtual evaluation and treatment models. The purpose of this article is to review current literature regarding the definition and prevalence of pediatric feeding disorder, the impact of the COVID-19 pandemic on parent/child stress and relationships surrounding feeding, and this speech-language pathologist's perception of both the positive and negative aspects of providing ongoing outpatient feeding evaluations and treatments in the context of the COVID-19 pandemic, as well as clinical considerations for ongoing feeding therapy after the COVID-19 pandemic.

Telepractice in the diagnosis and treatment of pediatric speech-language disorders: The opinions and experiences of speech-language pathologists.

PURPOSE: This prospective cross-sectional study aimed to investigate the opinions and experiences with telepractice (TP) of Dutch-speaking speech-language pathologists (SLPs) living in the Dutch-speaking part of Belgium (Flanders). This study will help to optimize care for children with speech-language disorders as we will gain more insight into the experienced barriers and facilitators while using TP for assessing and treating these disorders. METHOD: Twenty-nine Dutch-speaking speech-language pathologists living in Flanders (age category 20-30 years: n = 16/29, 55.2%, 31-40 years: n = 10/29, 34.2%, 41-50 years: n = 2/29, 6.9%, 51-60 years: n = 1/29, 3.4%) were recruited through the social media. An online questionnaire was developed based on the available literature and administered to the SLPs. To compare the opinions and experiences of SLPs with TP, χ2 tests or Fisher's exact tests were used. RESULTS: The study showed a statistically significant association between years of clinical experience of SLPs and their opinion that TP does not provide more options in a clinical setting compared to face-to-face contact. SLPs who had expertise in multiple domains experienced significantly more added value of TP during the corona pandemic than SLPs who had expertise in only one specific domain. Additionally, SLPs who worked in a private practice indicated significantly more difficulties in developing a therapeutic relationship due to a lack of personal contact than SLPs who worked in other settings. 51.7% (15/29) of the SLPs experienced technical barriers using TP. CONCLUSION: Expertise in multiple domains of pediatric speech-language therapy resulted in experiencing more added value of TP during the corona pandemic, possibly because of the experience of multiple different and simultaneous advantages of TP in several domains. Additionally, SLPs in a private practice experienced more difficulties in developing a therapeutic relationship due to a lack of personal contact with their clients. This is in contrast to hospitals where children are often seen for a shorter period. Hence, there may be less chance of a negative perception of relationships with clients. Another conclusion is that treatment drop-out was not larger using TP compared to face-to-face therapy. However, SLPs experienced that the use of TP was not promoted/encouraged by their employer possibly because of technical barriers. It is hoped that the findings of this study will help SLPs and policymakers overthrow existing barriers and make telepractice a substantial, effective, and efficient service delivery model.

The effects of face mask on speech production and its implication for forensic speaker identification-A cross-linguistic study.

This study aims to understand the effects of face mask on speech production between Mandarin Chinese and English, and on the automatic classification of mask/no mask speech and individual speakers. A cross-linguistic study on mask speech between Mandarin Chinese and English was then conducted. Continuous speech of the phonetically balanced texts in both Chinese and English versions were recorded from thirty native speakers of Mandarin Chinese (i.e., 15 males and 15 females) with and without wearing a surgical mask. The results of acoustic analyses showed that mask speech exhibited higher F0, intensity, HNR, and lower jitter and shimmer than no mask speech for Mandarin Chinese, whereas higher HNR and lower jitter and shimmer were observed for English mask speech. The results of classification analyses showed that, based on the four supervised learning algorithms (i.e., Linear Discriminant Analysis, Naïve Bayes Classifier, Random Forest, and Support Vector Machine), undesirable performances (i.e., lower than 50%) in classifying the speech with and without a face mask, and highly-variable accuracies (i.e., ranging from 40% to 89.2%) in identifying individual speakers were achieved. These findings imply that the speakers tend to conduct acoustic adjustments to improve their speech intelligibility when wearing surgical mask. However, a cross-linguistic difference in speech strategies to compensate for intelligibility was observed that Mandarin speech was produced with higher F0, intensity, and HNR, while English was produced with higher HNR. Besides, the highly-variable accuracies of speaker identification might suggest that surgical mask would impact the general performance of the accuracy of automatic speaker recognition. In general, therefore, it seems wearing a surgical mask would impact both acoustic-phonetic and automatic speaker recognition approaches to some extent, thus suggesting particular cautions in the real-case practice of forensic speaker identification.

Using speech-to-text technology to empower young writers with special educational needs.

This article reports the first group-based intervention study in the UK of using speech to-text (STT) technology to improve the writing of children with special educational needs and disabilities (SEND). Over a period of five years, thirty children took part in total from three settings; a mainstream school, a special school and a special unit of a different mainstream school. All children had Education, Health and Care Plans because of their difficulties in spoken and written communication. Children were trained to use the Dragon STT system, and used it on set tasks for 16-18 weeks. Handwritten text and self-esteem were assessed before and after the intervention, and screen-written text at the end. The results showed that this approach had boosted the quantity and quality of handwritten text, with post-test screen-written text significantly better than handwritten at post-test. The self-esteem instrument also showed positive and statistically significant results. The findings support the feasibility of using STT to support children with writing difficulties. All the data were gathered before the Covid-19 pandemic; the implications of this, and of the innovative research design, are discussed.

The role of science in a crisis: Talks by political leaders during the COVID-19 pandemic.

During the COVID-19 pandemic, science has been prominently featured in institutional communication and political agendas as never before. Governments substantially relied on scientific experts to analyze pandemic trends, develop anti-COVID-19 vaccines and adopt containment strategies. In this paper, we analyze speeches by three political leaders-Boris Johnson (Prime Minister, UK), Sergio Mattarella (President of the Republic, Italy), and Ursula von der Leyen (President, European Commission)-between February 20, 2020, and February 20, 2022, to identify how science was addressed and framed. The results of the quantitative and qualitative exploration of the speeches highlight three main ways in which political leaders view science: a national pride narrative-i.e., science as an instrument and indicator of national pride and international standing of the country; an ethical narrative-i.e., science as an agent of social growth; an integration narrative-i.e., science as a driving force of both European integration and stronger collaboration between knowledge production and industry. The predominant narrative varies in relation to the political leaders' different institutional contexts and roles.

Distinguish the Severity of Illness Associated with Novel Coronavirus (COVID-19) Infection via Sustained Vowel Speech Features.

The authors are currently conducting research on methods to estimate psychiatric and neurological disorders from a voice by focusing on the features of speech. It is empirically known that numerous psychosomatic symptoms appear in voice biomarkers; in this study, we examined the effectiveness of distinguishing changes in the symptoms associated with novel coronavirus infection using speech features. Multiple speech features were extracted from the voice recordings, and, as a countermeasure against overfitting, we selected features using statistical analysis and feature selection methods utilizing pseudo data and built and verified machine learning algorithm models using LightGBM. Applying 5-fold cross-validation, and using three types of sustained vowel sounds of /Ah/, /Eh/, and /Uh/, we achieved a high performance (accuracy and AUC) of over 88% in distinguishing "asymptomatic or mild illness (symptoms)" and "moderate illness 1 (symptoms)". Accordingly, the results suggest that the proposed index using voice (speech features) can likely be used in distinguishing the symptoms associated with novel coronavirus infection.

Stuttering-Like Dysfluencies as a Consequence of Long COVID-19.

PURPOSE: We present two patients who developed neurogenic stuttering after long COVID-19 related to SARS-CoV-2 infection. METHODS AND RESULTS: Both patients experienced both physical (e.g., fatigue) and cognitive difficulties, which led to impaired function of attention, lexical retrieval, and memory consolidation. Both patients had new-onset stuttering-like speech dysfluencies: Blocks and repetitions were especially evident at the initial part of words and sentences, sometimes accompanied by effortful and associated movements (e.g., facial grimaces and oro-facial movements). Neuropsychological evaluations confirmed the presence of difficulties in cognitive tasks, while neurophysiological evaluations (i.e., electroencephalography) suggested the presence of "slowed" patterns of brain activity. Neurogenic stuttering and cognitive difficulties were evident for 4-5 months after negativization of SARS-CoV-2 nasopharyngeal swab, with gradual improvement and near-to-complete recovery. CONCLUSIONS: It is now evident that SARS-CoV-2 infection may significantly involve the central nervous system, also resulting in severe and long-term consequences, even if the precise mechanisms are still unknown. In the present report, long COVID-19 resulted in neurogenic stuttering, as the likely consequence of a "slowed" metabolism of (pre)frontal and sensorimotor brain regions (as suggested by the present and previous clinical evidence). As a consequence, the pathophysiological mechanisms related to the appearance of neurogenic stuttering have been hypothesized, which help to better understand the broader and possible neurological consequences of COVID-19.

Views of Speech-Language Pathologists on Telepractice for Children Who Use Augmentative and Alternative Communication.

Telepractice has become increasingly utilized in disability services, particularly with recent and ongoing measures to slow the spread of the novel coronavirus (COVID-19). In this study, 361 speech-language pathologists (SLPs) responded to a national, web-based survey about their views on utilizing telepractice with children aged 3 to 21 who used aided augmentative and alternative communication (AAC), such as picture symbols or speech-generating devices. The views of SLPs varied, and SLPs who received training on AAC telepractice within the last 12 months had more positive views about telepractice than those who did not. Several factors were associated with when and how SLPs thought telepractice was beneficial to serve children who use aided AAC, including SLPs' foundational perspectives about telepractice, service delivery options, considerations related to the child and family, and broader resources and constraints.

Providing Telepractice in Schools During a Pandemic: The Experiences and Perspectives of Speech-Language Pathologists.

PURPOSE: The main objective of this study was to gain insight into school-based speech-language pathologists' (SLPs') perspectives on and experiences with telepractice as a service delivery model at the onset of the COVID-19 global pandemic. A better understanding of the facilitating and challenging factors that belie telepractice-based services will guide the creation of training and resource development to further support remote speech-language services in schools. METHOD: Four focus group sessions using a semistructured format were conducted with 22 school-based SLPs from 14 states in the United States. The focus groups provided an opportunity for SLPs to reflect on their telepractice experiences, including pros and cons, necessary knowledge and skills, factors impacting telepractice service delivery, and student and family participation. Inductive thematic analysis was used to describe the collective experiences and perspectives of the participants. RESULTS: Three themes regarding telepractice emerged: technology use, locus of control for decision making, and student and family engagement. Participants reported experiencing a range of successes and challenges when attempting to meet students' needs and identified gaps in resources and school capacity for telepractice. CONCLUSIONS: The findings revealed how school SLPs experienced telepractice service delivery during the remote learning portion of the 2019-2020 school year due to the onset of the COVID-19 pandemic. The study increases our understanding of factors that facilitated and challenged the effective delivery of speech-language services via telepractice. To assist SLPs in future telepractice efforts, implications for professional development and further research are provided.

School-Based Speech-Language Pathologists' Stress and Burnout: A Cross-Sectional Survey at the Height of the COVID-19 Pandemic.

PURPOSE: Low retention of school-based speech-language pathologists (SLPs) is a growing problem that can have drastic consequences at the school and student levels. Factors contributing to this shortage include features of the work environment, role ambiguity, low salaries, and a demanding workload with higher caseloads, which can result in limited time for paperwork and lesson planning for optimal service delivery models. The purpose of this study was to determine the current levels and predictors of occupational stress and burnout SLPs are experiencing in the school setting. METHOD: Using a cross-sectional survey design, 453 school-based SLPs from across the United States reported their workload manageability, career intentions, access to social support, and their stress and burnout levels. Multiple linear regression was used to determine the relation between the variables of interest and the occupational stress and burnout scores. Data were collected in September to December of 2020, at the height of the COVID-19 pandemic. RESULTS: SLPs, on average, reported overall stress levels in the somewhat noticeable range, moderate access to social support, high levels of emotional exhaustion, low-to-moderate feelings of depersonalization, and moderate-to-high feelings of personal accomplishments. Based on a standardized burnout scale, SLPs in this sample are characterized as feeling ineffective and overextended. Results of linear regression models suggest that the perception of work manageability was the best predictor of Total Stress score, Emotional Exhaustion score, and Depersonalization score, in this sample. CONCLUSIONS: Data from this study offer the beginning steps to making an informed change for school-based SLPs' workplaces. Results indicated that SLPs in the school setting are feeling ineffective and overextended. The perception of their workload manageability was the most significant predictor for their reported stress and burnout levels. Suggestions for SLP supervisors, administrators, and other stakeholders are discussed.

Dissociating COVID-19 from other respiratory infections based on acoustic, motor coordination, and phonemic patterns.

In the face of the global pandemic caused by the disease COVID-19, researchers have increasingly turned to simple measures to detect and monitor the presence of the disease in individuals at home. We sought to determine if measures of neuromotor coordination, derived from acoustic time series, as well as phoneme-based and standard acoustic features extracted from recordings of simple speech tasks could aid in detecting the presence of COVID-19. We further hypothesized that these features would aid in characterizing the effect of COVID-19 on speech production systems. A protocol, consisting of a variety of speech tasks, was administered to 12 individuals with COVID-19 and 15 individuals with other viral infections at University Hospital Galway. From these recordings, we extracted a set of acoustic time series representative of speech production subsystems, as well as their univariate statistics. The time series were further utilized to derive correlation-based features, a proxy for speech production motor coordination. We additionally extracted phoneme-based features. These features were used to create machine learning models to distinguish between the COVID-19 positive and other viral infection groups, with respiratory- and laryngeal-based features resulting in the highest performance. Coordination-based features derived from harmonic-to-noise ratio time series from read speech discriminated between the two groups with an area under the ROC curve (AUC) of 0.94. A longitudinal case study of two subjects, one from each group, revealed differences in laryngeal based acoustic features, consistent with observed physiological differences between the two groups. The results from this analysis highlight the promise of using nonintrusive sensing through simple speech recordings for early warning and tracking of COVID-19.

Development and validation of a machine learning-based vocal predictive model for major depressive disorder.

BACKGROUND: Variations in speech intonation are known to be associated with changes in mental state over time. Behavioral vocal analysis is an algorithmic method of determining individuals' behavioral and emotional characteristics from their vocal patterns. It can provide biomarkers for use in psychiatric assessment and monitoring, especially when remote assessment is needed, such as in the COVID-19 pandemic. The objective of this study was to design and validate an effective prototype of automatic speech analysis based on algorithms for classifying the speech features related to MDD using a remote assessment system combining a mobile app for speech recording and central cloud processing for the prosodic vocal patterns. METHODS: Machine learning compared the vocal patterns of 40 patients diagnosed with MDD to the patterns of 104 non-clinical participants. The vocal patterns of 40 patients in the acute phase were also compared to 14 of these patients in the remission phase of MDD. RESULTS: A vocal depression predictive model was successfully generated. The vocal depression scores of MDD patients were significantly higher than the scores of the non-patient participants (p < 0.0001). The vocal depression scores of the MDD patients in the acute phase were significantly higher than in remission (p < 0.02). LIMITATIONS: The main limitation of this study is its relatively small sample size, since machine learning validity improves with big data. CONCLUSIONS: The computerized analysis of prosodic changes may be used to generate biomarkers for the early detection of MDD, remote monitoring, and the evaluation of responses to treatment.

Intelligent speech technologies for transcription, disease diagnosis, and medical equipment interactive control in smart hospitals: A review.

The growing and aging of the world population have driven the shortage of medical resources in recent years, especially during the COVID-19 pandemic. Fortunately, the rapid development of robotics and artificial intelligence technologies help to adapt to the challenges in the healthcare field. Among them, intelligent speech technology (IST) has served doctors and patients to improve the efficiency of medical behavior and alleviate the medical burden. However, problems like noise interference in complex medical scenarios and pronunciation differences between patients and healthy people hamper the broad application of IST in hospitals. In recent years, technologies such as machine learning have developed rapidly in intelligent speech recognition, which is expected to solve these problems. This paper first introduces IST's procedure and system architecture and analyzes its application in medical scenarios. Secondly, we review existing IST applications in smart hospitals in detail, including electronic medical documentation, disease diagnosis and evaluation, and human-medical equipment interaction. In addition, we elaborate on an application case of IST in the early recognition, diagnosis, rehabilitation training, evaluation, and daily care of stroke patients. Finally, we discuss IST's limitations, challenges, and future directions in the medical field. Furthermore, we propose a novel medical voice analysis system architecture that employs active hardware, active software, and human-computer interaction to realize intelligent and evolvable speech recognition. This comprehensive review and the proposed architecture offer directions for future studies on IST and its applications in smart hospitals.

Telehealth Management of Dysphagia in Adults: A Survey of Speech Language Pathologists' Experiences and Perceptions.

The goal of this study was to explore telehealth use for dysphagia management in response to COVID-19 to understand variables associated with clinician confidence and perceived effectiveness of this service delivery model and determine clinician-perceived benefits and challenges of managing dysphagia via telehealth. Speech-language pathologists (SLPs, n = 235) completed a web-based survey, providing information on demographics, telehealth use during the pandemic, and perspectives on current and future tele-management of dysphagia. Analyses included descriptive statistics to examine usage patterns; logistic regression to determine which variables were associated with telehealth use, clinician confidence, and perceived-effectiveness; and conventional content analysis to analyze responses to open-ended questions. Results revealed a sharp increase in the tele-management of dysphagia during the pandemic. Years of experience with dysphagia management (p = .031) and pre-pandemic use of telehealth (p < .001) were significantly associated with current use patterns. Working in the outpatient setting was associated with greater clinician confidence (p = .003) and perceived effectiveness (p = .007), and use of guidelines (p = .042) was also associated with greater clinician confidence. Key challenges identified included inadequate technological infrastructure, inadequate patient digital literacy, and reimbursement restrictions. Key benefits were treatment continuity, improving access to care, and time savings. The majority (67%) of respondents reported that they would use telehealth in the future. These findings demonstrate SLPs' abilities and desire to expand their practice patterns to include telehealth for dysphagia management. Therefore, clinician training and more research on best practices for assessment and treatment of dysphagia via telehealth is warranted to refine models of care for dysphagia tele-management.

A novel multimodal fusion framework for early diagnosis and accurate classification of COVID-19 patients using X-ray images and speech signal processing techniques.

BACKGROUND AND OBJECTIVE: COVID-19 outbreak has become one of the most challenging problems for human being. It is a communicable disease caused by a new coronavirus strain, which infected over 375 million people already and caused almost 6 million deaths. This paper aims to develop and design a framework for early diagnosis and fast classification of COVID-19 symptoms using multimodal Deep Learning techniques. METHODS: we collected chest X-ray and cough sample data from open source datasets, Cohen and datasets and local hospitals. The features are extracted from the chest X-ray images are extracted from chest X-ray datasets. We also used cough audio datasets from Coswara project and local hospitals. The publicly available Coughvid DetectNow and Virufy datasets are used to evaluate COVID-19 detection based on speech sounds, respiratory, and cough. The collected audio data comprises slow and fast breathing, shallow and deep coughing, spoken digits, and phonation of sustained vowels. Gender, geographical location, age, preexisting medical conditions, and current health status (COVID-19 and Non-COVID-19) are recorded. RESULTS: The proposed framework uses the selection algorithm of the pre-trained network to determine the best fusion model characterized by the pre-trained chest X-ray and cough models. Third, deep chest X-ray fusion by discriminant correlation analysis is used to fuse discriminatory features from the two models. The proposed framework achieved recognition accuracy, specificity, and sensitivity of 98.91%, 96.25%, and 97.69%, respectively. With the fusion method we obtained 94.99% accuracy. CONCLUSION: This paper examines the effectiveness of well-known ML architectures on a joint collection of chest-X-rays and cough samples for early classification of COVID-19. It shows that existing methods can effectively used for diagnosis and suggesting that the fusion learning paradigm could be a crucial asset in diagnosing future unknown illnesses. The proposed framework supports health informatics basis on early diagnosis, clinical decision support, and accurate prediction.

Would you respect a norm if it sounds foreign? Foreign-accented speech affects decision-making processes.

Does listening to a foreign-accented speaker bias native speakers' behavior? We investigated whether the accent, i.e., a foreign accent versus a native accent, in which a social norm is presented affects native speakers' decision to respect the norm (Experiments 1 and 2) and the judgement for not respecting it (Experiment 2). In Experiment 1, we presented 128 native Spanish speakers with new social norms, adapted from the measures imposed by the Spanish Government to fight the Covid-19 pandemic (e.g., 'To avoid the spread of the Covid-19 virus, keep your distance'), whereas in Experiment 2, we presented 240 native Spanish speakers with everyday social norms learned from childhood (e.g., 'Not littering on the street or in public places'), that have an intrinsic cultural and linguistic link. In Experiment 1, the norms were uttered either in a native accent, or in a foreign accent unfamiliar to our participants to avoid stereotypes. In Experiment 2, we added an accent negatively perceived in Spain to assess the role of language attitudes on decision making. Overall, accent did not directly impact participants' final decisions, but it influenced the decision-making process. The factors that seem to underlie this effect are emotionality and language attitudes. These findings add up to the recent Foreign Accent effect observed on moral judgements and further highlight the role of the speaker's identity in decision making.

Speech Recognition and Listening Effort of Meaningful Sentences Using Synthetic Speech.

Speech-recognition tests are an important component of audiology. However, the development of such tests can be time consuming. The aim of this study was to investigate whether a Text-To-Speech (TTS) system can reduce the cost of development, and whether comparable results can be achieved in terms of speech recognition and listening effort. For this, the everyday sentences of the German Göttingen sentence test were synthesized for both a female and a male speaker using a TTS system. In a preliminary study, this system was rated as good, but worse than the natural reference. Due to the Covid-19 pandemic, the measurements took place online. Each set of speech material was presented at three fixed signal-to-noise ratios. The participants' responses were recorded and analyzed offline. Compared to the natural speech, the adjusted psychometric functions for the synthetic speech, independent of the speaker, resulted in an improvement of the speech-recognition threshold (SRT) by approximately 1.2 dB. The slopes, which were independent of the speaker, were about 15 percentage points per dB. The time periods between the end of the stimulus presentation and the beginning of the verbal response (verbal response time) were comparable for all speakers, suggesting no difference in listening effort. The SRT values obtained in the online measurement for the natural speech were comparable to published data. In summary, the time and effort for the development of speech-recognition tests may be significantly reduced by using a TTS system. This finding provides the opportunity to develop new speech tests with a large amount of speech material.