Non-nutritive sucking (NNS; sucking without nutrition delivery) is one of the earliest motor behaviors in infancy and has key connections to feeding. In research, NNS is typically assessed using contact-based devices that rely on sensorized pacifiers attached to pressure transducers. These methods may disrupt the infant’s natural sucking pattern and are limited to controlled environments. In clinical settings, less objective methods such as use of a gloved finger or observation are common. To overcome these limitations, our team has developed a suite of artificial intelligence (AI) and computer vision-based tools that enable contactless, video-based assessment of NNS. We first established proof-of-concept, comparing facial landmark-derived jaw movement signals from video recordings to data obtained from a contact-based NNS device. We created the first annotated infant facial landmark dataset (InfAnFace), improving the accuracy of a deep learning-based inference model across varied infant appearances and conditions. Then, we developed an end-to-end system capable of detecting and segmenting NNS behavior throughout extended video recordings. These advances have broad practical relevance for in-person and remote assessment of NNS, including in real-world settings. This technology has the potential to positively impact speech-language pathology clinical practice by supporting practical and objective assessment of NNS.

Meta-analyses are vital for synthesizing evidence to guide clinical practice, policy, and research. However, incomplete or inconsistent reporting often excludes intervention studies, especially in Communication Sciences and Disorders (CSD), where both group and single case designs are common. This article introduces the Intervention Study Reporting for Meta-Analysis (ISR-MA) tool, a research-informed framework designed to improve transparency and usability of intervention study reports. ISR-MA provides practical guidance on reporting essential elements such as sample characteristics, outcomes, effect sizes, intervention components, and fidelity. It also promotes data accessibility and open science alignment. Using examples from meta-analytic challenges, we show how ISR-MA can reduce reporting bias and increase study inclusion in syntheses. We highlight the roles of authors, reviewers, editors, and journals in advancing reporting standards. By enhancing alignment between reporting practices and meta-analytic needs, ISR-MA fosters greater rigor, visibility, and impact of intervention research, supporting a more accurate and equitable evidence base in CSD and related fields.

This paper invites dialogue on how artificial intelligence (AI) can enhance personal relevance in augmentative and alternative communication (AAC) systems. Personally relevant AAC, reflecting users’ interests, experiences, and preferred characters, may support communication, literacy, and self-expression. Emerging AI tools offer new opportunities for rapid, individualized personalization of AAC symbols and supports, but also raise challenges, including reproducibility, cultural sensitivity, privacy, copyright, and evidence-based assessment considerations. The intent of this forum format is two-fold: (a) to promote ongoing interdisciplinary discussion regarding AI-supported approaches to generating personally meaningful AAC displays, providing directions for future empirical research, and (b) to provide a starting point for clinicians to consider personalization within clinical practice that advances evidence-based AAC. Collaboration among clinicians, researchers, AAC users, and families is essential to ensure AI-integrated AAC systems are ethically developed, empirically evaluated, meaningful, and empowering to those who use AAC.

Advances in artificial intelligence have made high-fidelity voice cloning increasingly accessible for people living with amyotrophic lateral sclerosis (ALS). AI-driven systems can generate novel, highly realistic utterances from limited speech samples, offering new opportunities to preserve identity, relationships, and emotional nuance within augmentative and alternative communication (AAC). Yet, it introduces distinct risks that extend beyond traditional message and voice banking, including impersonation, loss of control, erosion of voice as a trusted identifier, and posthumous persistence of a personal “acoustical fingerprint.” Consequently, individuals with ALS and their families ask questions about autonomy, privacy, delegation, and long-term management of cloned voices. This paper describes the development and implementation of a practice-based, patient-centered framework for AI-enabled voice cloning. Developed iteratively through longitudinal clinical encounters, the framework is operationalized through a Guiding Principles document and planning aid addressing informed consent, preferences, and ongoing review as disease, technology, and priorities evolve. The framework addresses autonomy and incorporates safeguards related to access control, ownership, professional accountability, and posthumous use. Conceptual alignment with international data-protection and AI-governance principles, including the European Union’s General Data Protection Regulation, supports the framework’s broader relevance, offering an approach for ethical integration into AAC practice while protecting identity, autonomy, and long-term interests.

ABSTRACT This study is intended to identify current perceptions about artificial intelligence among speech-language pathology practices and services in children and adults. Focus group data from 9 speech-language pathologists – clinical supervisors (SLPs) in Greece and Cyprus services were used. The focus group answered a 9-item questionnaire, and the data were analyzed using qualitative thematic analysis to understand better perceptions of Artificial Intelligence among SLPs professionals. The findings revealed the primary themes of the SLPs who participated in the focus group. Specifically, it was reported that participants showed a positive attitude toward AI, recognizing its potential to enhance speech-language pathology services with accurate and efficient diagnostics and treatment. Concerns about the lack of human touch and data privacy/security were significant among them. Most participants agreed that SLPs should acquire knowledge of AI, data analysis, and technical skills to integrate AI effectively into their practice. This study revealed critical clinical implications derived from participants’ reports. It discusses the importance of rethinking the scope of practice of using AI when working with vulnerable populations.

Voice banking technologies are increasingly used to support individuals at risk of losing natural speech due to progressive or acquired conditions. While recent advances in AI-based voice cloning have expanded access to synthetic voice creation, these developments also raise important clinical, ethical, and relational considerations. This paper reframes voice banking through the lens of speech-language pathologists and other professionals involved in implementing this intervention, arguing that the process is not merely technical but also tied to preserving identity, autonomy, and human connection. Drawing on current perspectives and emerging practice, we explore challenges related to consent, posthumous voice use, data quality, and equity in access. We examine how voice banking intersects with linguistic identity, and why some individuals may make informed choices to decline. The emotional labor of clinicians facilitating these conversations in complex contexts is also highlighted, alongside the need for adequate professional supports. The paper calls for co-designed, inclusive systems that can accommodate diverse speech profiles and clinical contexts. Ultimately, ethical voice banking depends not just on technological capability, but on values-driven, person-centered care. Clinicians play a pivotal role in ensuring these tools are implemented thoughtfully, with attention to the relational dimensions of communication.

ABSTRACT Artificial intelligence (AI) has the opportunity to impact the field of augmentative and alternative communication (AAC). Specific populations may experience unique benefits of AI, including children with cortical visual impairment (CVI). Children with CVI present with a range of visual skills requiring attention when designing a supportive AAC interface. Currently, personalizing AAC interfaces for this population is often labor intensive for both clinicians and researchers. Systematic methods to modify AAC interfaces for this population are also lacking. This limits professionals in their ability to trial interface designs to determine the most effective options. Efforts to personalize AAC interfaces to reduce navigation demands, limit visual complexity, and ensure adequate symbolic representation could be bolstered with AI. A just-in-time (JIT) programming approach supported by AI may be beneficial to pursue as this technology offers the ability to make changes to elements quickly and efficiently. It is necessary to consider how AAC interfaces may leverage AI to provide children with CVI interfaces that are easy to navigate and use during interactions with communication partners. This paper will propose possible avenues for AI specifically as it relates to possible JIT programming development opportunities for children with CVI.