A large-scale comparison of two voice synthesis techniques on intelligibility, naturalness, preferences, and attitudes toward voices banked by individuals with amyotrophic lateral sclerosis

Amyotrophic lateral sclerosis (ALS) commonly results in the inability to produce natural speech, making speech-generating devices (SGDs) important. Historically, synthetic voices generated by SGDs were neither unique, nor age- or dialect-appropriate, which depersonalized SGD use. Voices generated by SGDs can now be customized via voice banking and should ideally sound uniquely like the individual's natural speech, be intelligible, and elicit positive reactions from communication partners. This large-scale 2 x 2 mixed between- and within-participants design examined perceptions of 831 adult listeners regarding custom synthetic voices created for two individuals diagnosed with ALS via two synthesis systems in common clinical use (waveform concatenation and statistical parametric synthesis). The study explored relationships among synthesis system, dysarthria severity, synthetic speech intelligibility, naturalness, and preferences, and also provided a preliminary examination of attitudes regarding the custom synthetic voices. Synthetic voices generated via statistical parametric synthesis trained on deep neural networks were more intelligible, natural, and preferred than voices produced via waveform concatenation, and were associated with more positive attitudes. The custom synthetic voice created from moderately dysarthric speech was more intelligible than the voice created from mildly dysarthric speech. Clinical implications and factors that may have contributed to the relative intelligibilities are discussed.

Speech-language pathologist involvement in the paediatric intensive care unit

PURPOSE

To measure the prevalence of speech-language pathologist (SLP) involvement and associated trends for critically ill children in United States (US) paediatric intensive care units (PICU) through secondary analysis of the Prevalence of Acute Rehab for Kids in the PICU (PARK-PICU) study data.

METHOD

A secondary analysis of cross-sectional point prevalence study conducted over 1 day in 82 US PICUs. Data collected included SLP presence, patients' age, length of stay, medical interventions, aetiology, admission data, Glasgow Coma Scale scores, staffing involvement, and family presence.

RESULT

Among 961 patients, 82 were visited by an SLP on the study day for a prevalence of 8.5%. Most visits were for children <3 years old. The odds of SLP involvement were lower for children who were 7-12 years old (vs. age 0-2; adjusted odds ratio [aOR] 0.28; 95% CI 0.1-0.8), were mechanically ventilated via endotracheal tube (vs. room air; aOR 0.02; 95% CI 0.005-0.11), or had mild or severe disability (mild vs. no disability; aOR 0.34; 95% CI 0.16-0.76 and severe vs. no disability; aOR 0.39; 95% CI 0.17-0.90). Concurrent physical and/or occupational therapy involvement was associated with higher odds of SLP involvement (aOR 3.6; 95% CI 2.1-6.4).

CONCLUSION

SLP involvement is infrequent in US PICUs. PICU teams should be educated about the scope of SLP practice, to support communication and oral feeding needs during early recovery from critical illness.

The BCH message banking process™, voice banking, and double-dipping™

Significant advances have been made in interventions to maintain communication and personhood for individuals with neurodegenerative conditions. One innovation is Message Banking, a clinical approach first developed at Boston Children's Hospital (BCH). This paper outlines the Message Banking process as implemented at BCH, which includes the option of "Double Dipping," where banked messages are mined to develop personalized synthesized voices. More than a decade of experience has led to the evolution of six core principles underpinning the BCH process, resulting in a structured introduction of the associated concepts and practices with people with amyotrophic lateral sclerosis (ALS) and their families. These principles highlight the importance of assigning ownership and control of the process to individuals with ALS and their families, ensuring that as a tool it is empowering and offers hope. Changes have been driven by feedback from individuals who have participated in the BCH process over many years. The success of the process has recently been extended through partnerships that allow the recorded messages to be used to develop individual personalized synthetic voices to complement banked messages. While the process of banking messages is technically relatively simple, the full value of the process should be underpinned by the values and principles outlined in this tutorial.

Speech-language pathologists in paediatric palliative care: a Delphi study protocol

Background

Given the dearth of literature and no clinical practice guidelines written for speech-language pathologists (SLPs) working in paediatric palliative care (PPC), a need has been identified to explore the scope of clinical practice and strategies used by SLPs.

Objective

This study aims to undertake an international investigation into the role and scope of practice of SLPs working in PPC to develop consensus-driven ‘Recommendations for Speech-Language Pathologists in Paediatric Palliative Care Teams’ (ReSP3CT).

Methods

A modified Delphi process will be used to synthesise consensus-based statements from SLPs in six different countries about their role and practice working in PPC. Initially, preliminary survey data will be collected from SLPs to obtain demographic and caseload information. Respondents will then be invited to participate in an in-depth interview to explore common and unique themes that emerge from the online survey. Participants from the interview will then ‘opt-in’ to become Delphi panel members and receive questionnaires comprising statements for agreement over multiple rounds. Statements will be based on common themes that arise from the literature review, survey and interview data. The Delphi process for each statement will stop if statements achieve ≥ 70 % agreement and an IQR of ≤ 1 (maximum of five rounds).

Conclusion

This is the first study to investigate the role and practice of SLPs in PPC across internationally accepted scope of practice areas. The study will use existing frameworks for statistical analysis and a mixed-methods approach to aid in the synthesis of statements/recommendations for international consensus.

Speech-language pathology in paediatric palliative care: A scoping review of role and practice

PURPOSE

Attempts have been made within the literature to clarify the role and scope of speech-language pathologists (SLPs) within paediatric palliative care (PPC). As SLP literature regarding adult/geriatric populations is gaining traction, it is fitting to investigate the role of SLPs in the management of infants and children in end-of-life care.

METHOD

Arksey and O'Malley's ( 2005 ) scoping review method was utilised for searching multiple databases. Two database searches were undertaken. The first located literature in which SLP PPC intervention is specifically addressed. The second search utilised internationally recognised SLP scope of practice areas. Manual searching of reference lists was also utilised.

RESULT

Themes identified included management of communication, feeding, upper-airway and oral health as well as the role of SLPs within a multidisciplinary PPC team.

CONCLUSION

There is acknowledgement that SLPs have a role in PPC. However, there is little information identifying SLP involvement in the diagnosis and management of swallowing, cognition/communication, oral hygiene and upper airway issues. The available literature predominantly relies on limited adult palliative care research and does not address age-specific management approaches across the paediatric life-stage. Given an absence of SLP PPC guidelines, further research is warranted to explicitly define SLP scope of practice within this population.

Communication aid requirements of intensive care unit patients with transient speech loss

Alert and transiently nonvocal intensive care unit (ICU) patients are dependent on augmentative and alternative communication (AAC). Unfortunately, the literature demonstrates that existent AAC devices have not been widely adopted, and unaided methods are often the primary modalities used despite being insufficient, and frustrating. We present the results of a qualitative semi-structured interview study with 8 ex-ICU patients, 4 ICU patient relatives, and 6 ICU staff, exploring their AAC needs and requirements. Participants identified important AAC hardware, software, and content requirements. Salient factors impacting on AAC adoption in the ICU setting were also highlighted and included the need for staff training and bedside patient assessment. Based on the study results, we propose a series of recommendations regarding the design and implementation of future AAC tools specifically targeted at this group.

AAC Assessment and Intervention in Pediatric ICU/Acute Care: From Referral Through Continuum of Care

AAC supports in the ICU/Acute Care vary by patient presentation. Our 20+ years of bedside service delivery reveals trends in patient needs for AAC across the continuum of care. We detail three phases of AAC assessment and intervention and the role of SLP in the assessment/feature matching process.