Naturalistic Communication Research Articles

A Wearable AI-Driven Mask with Humidity-Sensing Respiratory Microphone for Non-Vocal Communication.

Hoarseness and dysphonia caused by vocal cord conditions or laryngeal surgeries significantly hinder communication and quality of life. This study presents a plug-and-play humidity-sensing respiratory microphone (HSRM) with generalized features for individual users. Leveraging gold nanoparticle-based humidity sensors integrated into commercially available wearable face masks, the system enables patients to produce verbal communication without relying on vocal cord activity. By integrating nanoparticle-enhanced humidity sensors with advanced convolutional neural networks, the HSRM system accurately decodes respiratory patterns into intelligible speech, achieving a recognition accuracy of 85.61%. Leveraging nanoparticle-polymer interfaces that effectively convert atmospheric humidity fluctuations into precise electrical signals, the system pioneers a contactless and non-invasive paradigm in assistive speech technology. This innovation addresses limitations of existing devices, such as reliance on residual vocal fold vibrations or skin-contact sensors, offering a practical generalized solution for individuals with aphonia. With its potential to facilitate naturalistic communication and transform healthcare applications, the HSRM system sets a new benchmark in wearable assistive technologies for voice rehabilitation and human-machine interaction.

A streaming brain-to-voice neuroprosthesis to restore naturalistic communication.

Natural spoken communication happens instantaneously. Speech delays longer than a few seconds can disrupt the natural flow of conversation. This makes it difficult for individuals with paralysis to participate in meaningful dialogue, potentially leading to feelings of isolation and frustration. Here we used high-density surface recordings of the speech sensorimotor cortex in a clinical trial participant with severe paralysis and anarthria to drive a continuously streaming naturalistic speech synthesizer. We designed and used deep learning recurrent neural network transducer models to achieve online large-vocabulary intelligible fluent speech synthesis personalized to the participant's preinjury voice with neural decoding in 80-ms increments. Offline, the models demonstrated implicit speech detection capabilities and could continuously decode speech indefinitely, enabling uninterrupted use of the decoder and further increasing speed. Our framework also successfully generalized to other silent-speech interfaces, including single-unit recordings and electromyography. Our findings introduce a speech-neuroprosthetic paradigm to restore naturalistic spoken communication to people with paralysis.

First-person pronouns as linguistic markers of depression among Brazilian youths.

Major depressive disorder (MDD) is a leading cause of disability among youth, yet identifying this condition remains challenging. Naturalistic communication offers a promising approach to enhance depression detection. Increased use of first-person singular pronouns (e.g., ''I'') has been linked to MDD, but its applicability to younger, non-English-speaking populations remains unclear. This study examined first-person pronoun use in Brazilian Portuguese-speaking adolescents with and without MDD and its relationship to self-reported and clinician-rated depressive symptoms. Fifty-two adolescents (13 with and 39 without MDD) from the Identifying Depression Early in Adolescence Risk Stratified Cohort (IDEA-RiSCo) sample completed remote data collection using a WhatsApp chatbot, responding to questions via audio recordings. Transcripts were analyzed using the Linguistic Inquiry and Word Count (LIWC). The MDD group used significantly more I-pronouns than non-MDD subjects (9.15 vs. 8.02%, t = -2.302, p = 0.026). Self-reported depressive symptomatology correlated with I-pronoun use (rho = 0.366, p = 0.008), but did not reach statistical significance for clinician-rated symptoms (rho = 0.248, p = 0.076). These findings support first-person singular pronouns as a potential linguistic marker of depression among Brazilian adolescents. This is the first study to replicate such results in a young, non-English-speaking sample using spoken speech, suggesting that integrating linguistic analysis with digital tools could enhance early detection efforts, particularly in resource-limited settings. Future research should explore use of I-pronouns alongside other linguistic and acoustic features to refine digital mental health screening approaches.

Feedback matters: EEG correlates of empathy involved in the naturalistic communication of emotions

Empathy involves the processing of complex information related to dynamic interactions between the empathizer and target. One neural signature of empathy is the suppression of electroencephalographic mu rhythm (8–13 Hz) over the sensorimotor region. It is important to consider that few researchers have studied the effects of empathizer feedback on empathy and its underlying neural mechanism, and most previous research has lacked ecological validity due to standardized emotional stimuli and constraints on the experiment environment. Our objective in this study was to investigate the means by which empathizer feedback influences one's own empathy in naturalistic social situations. Our results revealed that empathizer feedback decreases empathic accuracy but does not affect the emotional contagion nor the emotional intensity of the empathizer. We also found that the ability to accurately infer sadness is hindered by empathizer feedback. Empathizers presented lower alpha activity in the sensorimotor cortical areas only while receiving sad narratives and not providing feedback. This study contributes to the emerging research on the influence of empathizer feedback in naturalistic social settings.

Young children’s language socialisation to baby talk and ontology of infancy in a small rural Indo-Fijian community

This qualitative ethnographic research explores baby talk (BT) and ontology of infancy in a small, rural Indo-Fijian community via semistructured interviews with mothers about their children’s language learning, mothers’ narratives about their photographs of their young children engaged in everyday language, and audio- and video-recordings of naturalistic communication with and around 11 young children in their home environments. Analyses draw on Bourdieu’s notion of habitus, Ochs and Schieffelin’s child-centred and situation-centred categorisations, and de León’s approach to understanding language socialisation in multiparty participation frameworks. The findings describe: i) features of local BT, ii) local beliefs about babies, language acquisition and BT, iii) how local speakers’ communications with babies fit Ochs and Schieffelin’s categories, and iv) how young children draw on their elders’ BT to continue their community’s ways of interacting with and thinking about babies. The conclusion provides implications for pedagogy in early childhood education and care settings.

An Interprofessional Graduate Student and Family Coaching Program in Naturalistic Communication Techniques.

Researchers implemented a short-term cascading coaching model focusing on naturalistic developmental behavioral intervention with three participant triads. Triads consisted of a graduate student clinician, a minimally verbal child with autism spectrum disorder, and the child's parent. Coaching and intervention occurred during an interprofessional summer clinic that included graduate student clinicians from special education and speech and hearing sciences departments. The efficacy of short-term instruction, researcher coaching for student clinicians, and student clinician coaching of parents was evaluated using a multiple baseline across participants' design. The dependent variables were student clinician's and parent's use of elicitation techniques (creating communication temptations, waiting, and prompting) and response techniques (naturally reinforcing children's communication and providing spoken language models). Following coaching, parents and student clinicians from all triads increased their use of elicitation and response techniques, with very large effect sizes across all variables. Visual analysis findings suggest individualized differences and variability across triads. Implications for graduate education and parent coaching programs are discussed.

A day in the life: Couples' everyday communication and subsequent relationship outcomes.

Understanding how communication processes contribute to well-functioning versus distressed couple relationships has relied largely on brief, laboratory-based conversations. Harnessing technological advancements, the present study extends the literature by capturing couples' naturalistic communication over one full day at Time 1 (T1). This study tested associations between data-driven categories of couple communication behaviors and relationship outcomes (i.e., relationship aggression, satisfaction, and dissolution) at Time 2 (T2), approximately 1 year later. Emerging adults in different-gender dating couples (n = 106 couples; 212 individuals; Mage = 22.57 ± 2.44; M relationship length = 30.49 months ± 24.05; 72.2% non-White) were each provided a smartphone programmed to audio record approximately 50% of a typical day. Interactions between partners were transcribed and coded for location, activity, affect, and a range of positive and negative communication behaviors for each partner. Even after controlling for T1 assessments of the relevant outcome, one's own hostility and one's partner's hostility at T1 were each positively associated with T2 relationship aggression and negatively associated with T2 relationship satisfaction. One's own withdrawal at T1 was positively associated with T2 relationship aggression perpetration, whereas one's partner's withdrawal was negatively linked to relationship satisfaction at T2. One's own playfulness, unexpectedly, was linked to lower subsequent relationship satisfaction. Withdrawal increased the likelihood of relationship dissolution, whereas warmth and playfulness decreased the likelihood of dissolution. The relevance of couples' ordinary, everyday communication for meaningful relationship outcomes is discussed. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Meaningful Communication but not Superficial Anthropomorphism Facilitates Human-Automation Trust Calibration: The Human-Automation Trust Expectation Model (HATEM).

The objective was to demonstrate anthropomorphism needs to communicate contextually useful information to increase user confidence and accurately calibrate human trust in automation. Anthropomorphism is believed to improve human-automation trust but supporting evidence remains equivocal. We test the Human-Automation Trust Expectation Model (HATEM) that predicts improvements to trust calibration and confidence in accepted advice arising from anthropomorphism will be weak unless it aids naturalistic communication of contextually useful information to facilitate prediction of automation failures. Ninety-eight undergraduates used a submarine periscope simulator to classify ships, aided by the Ship Automated Modelling (SAM) system that was 50% reliable. A between-subjects 2 × 3 design compared SAM appearance (anthropomorphic avatar vs. camera eye) and voice inflection (monotone vs. meaningless vs. meaningful), with the meaningful inflections communicating contextually useful information about automated advice regarding certainty and uncertainty. Avatar SAM appearance was rated as more anthropomorphic than camera eye, and meaningless and meaningful inflections were both rated more anthropomorphic than monotone. However, for subjective trust, trust calibration, and confidence in accepting SAM advice, there was no evidence of anthropomorphic appearance having any impact, while there was decisive evidence that meaningful inflections yielded better outcomes on these trust measures than monotone and meaningless inflections. Anthropomorphism had negligible impact on human-automation trust unless its execution enhanced communication of relevant information that allowed participants to better calibrate expectations of automation performance. Designers using anthropomorphism to calibrate trust need to consider what contextually useful information will be communicated via anthropomorphic features.

Real-Time Deep Neurolinguistic Learning Enhances Noninvasive Neural Language Decoding for Brain-Machine Interaction.

Electroencephalogram (EEG)-based brain-machine interface (BMI) has been utilized to help patients regain motor function and has recently been validated for its use in healthy people because of its ability to directly decipher human intentions. In particular, neurolinguistic research using EEGs has been investigated as an intuitive and naturalistic communication tool between humans and machines. In this study, the human mind directly decoded the neural languages based on speech imagery using the proposed deep neurolinguistic learning. Through real-time experiments, we evaluated whether BMI-based cooperative tasks between multiple users could be accomplished using a variety of neural languages. We successfully demonstrated a BMI system that allows a variety of scenarios, such as essential activity, collaborative play, and emotional interaction. This outcome presents a novel BMI frontier that can interact at the level of human-like intelligence in real time and extends the boundaries of the communication paradigm.

Entropy for team communication pattern recognition

Entropy for team communication pattern recognition

Decoding lexical tones and vowels in imagined tonal monosyllables using fNIRS signals

Objective. Speech is a common way of communication. Decoding verbal intent could provide a naturalistic communication way for people with severe motor disabilities. Active brain computer interaction (BCI) speller is one of the most commonly used speech BCIs. To reduce the spelling time of Chinese words, identifying vowels and tones that are embedded in imagined Chinese words is essential. Functional near-infrared spectroscopy (fNIRS) has been widely used in BCI because it is portable, non-invasive, safe, low cost, and has a relatively high spatial resolution. Approach. In this study, an active BCI speller based on fNIRS is presented by covertly rehearsing tonal monosyllables with vowels (i.e. /a/, /i/, /o/, and /u/) and four lexical tones in Mandarin Chinese (i.e. tones 1, 2, 3, and 4) for 10 s. Main results. fNIRS results showed significant differences in the right superior temporal gyrus between imagined vowels with tone 2/3/4 and those with tone 1 (i.e. more activations and stronger connections to other brain regions for imagined vowels with tones 2/3/4 than for those with tone 1). Speech-related areas for tone imagery (i.e. the right hemisphere) provided majority of information for identifying tones, while the left hemisphere had advantages in vowel identification. Having decoded both vowels and tones during the post-stimulus 15 s period, the average classification accuracies exceeded 40% and 70% in multiclass (i.e. four classes) and binary settings, respectively. To spell words more quickly, the time window size for decoding was reduced from 15 s to 2.5 s while the classification accuracies were not significantly reduced. Significance. For the first time, this work demonstrated the possibility of discriminating lexical tones and vowels in imagined tonal syllables simultaneously. In addition, the reduced time window for decoding indicated that the spelling time of Chinese words could be significantly reduced in the fNIRS-based BCIs.

Telehealth Training in Naturalistic Communication Intervention for Mothers of Children with Angelman Syndrome.

Objectives Young children with Angelman syndrome have significant delays in expressive communication. Parents of children with Angelman syndrome require training to support their child’s communication development. Unfortunately, parent training focused on the needs of families of children with rare genetic syndromes is unavailable to many families. The purpose of this study was to evaluate a telehealth parent training program on naturalistic communication intervention for young children with Angelman syndrome.MethodsUsing two single-case multiple baseline designs across a total of six parent–child dyads, we evaluated the effects of a telehealth parent training program on parent implementation fidelity of a naturalistic communication intervention, child communication, and child engagement.ResultsWith the telehealth parent training program, parent implementation fidelity of naturalistic communication intervention improved, maintained and generalized to untrained home routines. Small effects on child communication and engagement were observed during the program.ConclusionsParents of children with Angelman syndrome were successfully taught via telehealth to implement a naturalistic communication intervention with their child at home. Additional research is needed to promote positive child communication outcomes through parent-mediated intervention.

Towards Naturalistic Speech Decoding from Intracranial Brain Data.

Speech decoding from brain activity can enable development of brain-computer interfaces (BCIs) to restore naturalistic communication in paralyzed patients. Previous work has focused on development of decoding models from isolated speech data with a clean background and multiple repetitions of the material. In this study, we describe a novel approach to speech decoding that relies on a generative adversarial neural network (GAN) to reconstruct speech from brain data recorded during a naturalistic speech listening task (watching a movie). We compared the GAN-based approach, where reconstruction was done from the compressed latent representation of sound decoded from the brain, with several baseline models that reconstructed sound spectrogram directly. We show that the novel approach provides more accurate reconstructions compared to the baselines. These results underscore the potential of GAN models for speech decoding in naturalistic noisy environments and further advancing of BCIs for naturalistic communication. Clinical Relevance - This study presents a novel speech decoding paradigm that combines advances in deep learning, speech synthesis and neural engineering, and has the potential to advance the field of BCI for severely paralyzed individuals.

A Module-Based Telepractice Intervention for Parents of Children with Developmental Disabilities.

In the current study, we describe a study of the Internet-based Parent-implemented Communication Strategies-Storybook (i-PiCSS). I-PiCSS is an intervention program designed to train and coach parents to use evidence-based naturalistic communication teaching (NCT) strategies (i.e., modeling, mand-model, and time delay) and reading techniques while reading storybooks with their young children with disabilities. Three participating parents were trained via online modules and coached via telepractice technologies (videoconferences). Zoom videoconference software was used for all coaching sessions. Using a single case multiple-baseline design across NCT strategies within each family, we examined, (a) parents' fidelity use of the three NCT strategies, (b) parents' use of book reading techniques, and (c) child language and communication outcomes. After self-directed training and remote coaching, parents used modeling, mand-model, and time delay strategies with higher rates and fidelity (accuracy). Children initiated more communicative acts upon parents' use of time delay and increased their numbers of single-and multiple-word responses.

Private and social speech in children with and without Attention Deficit Hyperactivity Disorder within a naturalistic communication setting

Objective: We analyzed to what extent dyads (pairs) of Finnish children with Attention Deficit Hyperactivity Disorder (ADHD) may show some limitations in private and social speech production within a dyadic communication setting. Method: Forty children with Typical Development (TD) and 28 children with ADHD from Finland participated in the study. They received a comprehensive evaluation of ADHD and IQ. Their parents answered a background questionnaire. Children were paired according to several variables, including diagnostic status (ADHD/TD) and age (8- or 10-year-olds). We examined private and social speech use within child dyads during play with a Lego set. The speech category analyses included inaudible private speech (muttering and whispering), silence (inner speech), and task-relevant or task-irrelevant private/social speech categories. Results: At 10 years of age, children with ADHD produced significantly less inaudible private speech and task-relevant private speech, as well as more task-irrelevant social speech, than age-matched children with TD. Furthermore, children with TD at 10 years of age produced significantly more inaudible private speech than 8-year-olds with TD. Conclusions: At 10 years of age, children with ADHD demonstrated delayed private speech internalization and difficulties in producing on-task self-directed speech as well as inhibiting task-irrelevant social speech, relative to same-age children with TD during social interaction with a peer. Typically developing children demonstrated a shift toward private speech internalization with age, from 8 to 10 years of age. Cross-cultural issues, setting effects, and clinical implications are discussed.

The Cultural and Linguistic Adaptation of a Caregiver-Implemented Naturalistic Communication Intervention

The Cultural and Linguistic Adaptation of a Caregiver-Implemented Naturalistic Communication Intervention

A Parent-Implemented Shared Reading Intervention via Telepractice

We describe a study of the internet-based Parent-Implemented Communication Strategies–Storybook (i-PiCSS), an intervention designed to train and coach parents to use evidenced-based naturalistic communication teaching (NCT) strategies (i.e., modeling, mand-model, and time delay) and RTs while reading storybooks with their young children with disabilities. Three participating parents were trained and coached via telepractice technologies (videoconferences, video editing software). Zoom software was used for videoconferencing and Camtasia software was used to record the training and coaching sessions and to edit the recorded session for feedback delivery purposes. Using a single-case multiple-baseline design across NCT strategies within each family, we examined (a) parents’ fidelity use of the three NCT strategies, (b) parents’ use of book RTs, and (c) child language and communication outcomes. The entire intervention period lasted 8 weeks. After training and coaching, parents used the modeling, mand-model, and time delay strategies with higher rates and higher quality (accuracy). Children initiated more communicative acts upon parents’ use of time delay and increased their numbers of single- and multiple-word responses.

Discourse Markers Activate Their, Like, Cohort Competitors

ABSTRACT Speech in everyday conversations is riddled with discourse markers (DMs), such as well, you know, and like. However, in many lab-based studies of speech comprehension, such DMs are typically absent from the carefully articulated and highly controlled speech stimuli. As such, little is known about how these DMs influence online word recognition. The present study specifically investigated the online processing of DM like and how it influences the activation of words in the mental lexicon. We specifically targeted the cohort competitor (CC) effect in the Visual World Paradigm: Upon hearing spoken instructions to “pick up the beaker,” human listeners also typically fixate—next to the target object—referents that overlap phonologically with the target word (cohort competitors such as beetle; CCs). However, several studies have argued that CC effects are constrained by syntactic, semantic, pragmatic, and discourse constraints. Therefore, the present study investigated whether DM like influences online word recognition by activating its cohort competitors (e.g., lightbulb). In an eye-tracking experiment using the Visual World Paradigm, we demonstrate that when participants heard spoken instructions such as “Now press the button for the, like … unicycle,” they showed anticipatory looks to the CC referent (lightbulb)well before hearing the target. This CC effect was sustained for a relatively long period of time, even despite hearing disambiguating information (i.e., the /k/ in like). Analysis of the reaction times also showed that participants were significantly faster to select CC targets (lightbulb) when preceded by DM like. These findings suggest that seemingly trivial DMs, such as like, activate their CCs, impacting online word recognition. Thus, we advocate a more holistic perspective on spoken language comprehension in naturalistic communication, including the processing of DMs.

Naturalistic Communication Training for Early Intervention Providers and Latinx Parents of Children with Signs of Autism.

In this study, researchers implemented a brief training plus coaching program in naturalistic developmental behavioral intervention with three participant triads. Each triad consisted of an early intervention provider, an English-speaking Latinx parent, and that parent’s young child with autism spectrum disorder (ASD) or early signs of ASD who had limited vocal speech. The effects a single training session, plus two researcher coaching sessions were evaluated using a nonconcurrent multiple probes across participants design. Primary dependent variables included (a) the number of completed targeted communication turns between the parent and child and (b) the number of child independent target communication responses (gestures and manual signs) during family-selected routines. Additional measures examined whether parents used strategies taught to them during training, and whether early intervention providers addressed strategies taught via coaching. A social validity measure was used to determine parent and provider views of the training. Due to COVID-19 restrictions, training and post-training sessions were delivered via telehealth for two triads. While data trends and variability differed across triads, following training, all three families increased the number of completed target communication turns and all three children showed higher rates of independent communication responses. Parents and providers implemented strategies taught and reported positive effects of the program. Implications regarding the use of naturalistic intervention methods for Latinx families, the utility of brief training models to meet the needs of under-resourced early intervention programs, and potential uses of telehealth are discussed.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10882-021-09794-w.

Referential Communication Between Friends and Strangers in the Wild

The Map Task (Anderson et al., 1991) and Tangram Task (Clark & Wilkes-Gibbs, 1986) are traditional referential communication tasks that are used in psycholinguistics research to demonstrate how conversational partners mutually agree on descriptions (or referring expressions) for landmarks or unusual target objects. These highly-controlled, laboratory-based tasks take place under conditions that are relatively unusual for naturally-occurring conversations (Speed, Wnuk, & Majid, 2016). In this study, we used the Artwalk Task (Liu, Fox Tree, & Walker, 2016) – a real world-situated blend of the Map Task and Tangram Task – to demonstrate that the process of negotiating referring expressions ‘in the wild’ is similar to the process that takes place in a laboratory. In Artwalk, participant pairs communicated via a Skype-to-mobile phone connection. One participant guided the other through a small downtown area with the goal of identifying public art objects, finding objects twice during two rounds. In addition to replicating laboratory results, we also found that acquaintanceship and extraversion influenced the number of unique descriptors used by dyads in this task. In Round 1, introverts in stranger dyads used fewer descriptors but introverts in friend dyads were indistinguishable from extraverts. The influence of extraversion declined by Round 2. This study suggests that referent negotiation observed in labs is generalizable but that naturalistic communication is subject to social and personality factors that may not be as influential in laboratory conditions.