How effective is LENA in detecting speech vocalizations and language produced by children and adolescents with ASD in different contexts?

The Predictability of Naturalistic Evaluation of All-Day Recordings for Speech and Language Development

OBJECTIVES

The study aimed to investigate the predictive potential of language environment and vocal development status measures obtained through integrated analysis of Language ENvironment Analysis (LENA) recordings during the prelinguistic stage for subsequent speech and language development in Korean-acquiring children. Specifically, this study explored whether measures from both LENA-automated analysis and human coding at 6-8 months and 12-14 months of age predict vocabulary and phonological development at 18-20 months.

METHOD

One-day home recordings from 20 children were collected using a LENA recorder at 6-8 months, 12-14 months, and 18-20 months. Both LENA-automated measures and measures from human coding were obtained from recordings at 6-8 months and 12-14 months. The number of different words, consonant inventory, and utterance structure inventory were identified from recordings of 18-20 months. Correlation and multiple regression analyses were performed to investigate whether measures related to early language environment and child vocalization at 6-8 months and 12-14 months were predictive of vocabulary and phonological measures at 18-20 months.

RESULTS

The results showed that the two main LENA-automated measures, conversational turn count (CTC) and child vocalization count, were positively correlated with all vocabulary and phonological measures at 18-20 months. Multiple regression analysis revealed that CTC during the prelinguistic stages was the most significant predictor of a number of different words, consonant inventory, and utterance structure inventory at 18-20 months. Also, adult word count in LENA-automated measures, child-directed speech ratio, and canonical babbling ratio measured by human coding significantly predicted some vocabulary and phonological measures at 18-20 months.

CONCLUSION

This study highlights the multifaceted nature of language acquisition and collectively emphasizes the value of considering both quantitative and qualitative aspects of language input to understand early language development in children.

Adaptive thresholding increases sensitivity to detect changes in the rate of skin conductance responses to psychologically arousing stimuli in both laboratory and ambulatory settings

Psychophysiologists recording electrodermal activity (EDA) often derive measures of slow, tonic activity-skin conductance level (SCL)-and faster, more punctate changes-skin conductance responses (SCRs). A SCR is conventionally considered to have occurred when the local amplitude of the EDA signal exceeds a researcher-determined threshold (e.g., 0.05 μS), typically fixed across study participants and conditions. However, fixed SCR thresholds can preferentially exclude data from individuals with low SCL because their SCRs are smaller on average, thereby reducing statistical power for group-level analyses. Thus, we developed a fixed plus adaptive (FA) thresholding method that adjusts identification of SCRs based on an individual's SC at the onset of the SCR to increase statistical power and include data from more participants. We assess the utility of applying FA thresholding across two independent samples and explore age and race-related associations with EDA outcomes. Study 1 uses wired EDA measurements from 254 healthy adults responding to evocative images and sounds in a laboratory setting. Study 2 uses wireless EDA measurements from 20 children with autism in a clinical environment while they completed behavioral tasks. Compared to a 0.01, 0.03, and 0.05 μS fixed threshold, FA thresholding at 1.9% modestly increases statistical power to detect a difference in SCR rate between tasks with higher vs. lower subjective arousal and reduces exclusion of participants by up to 5% across both samples. This novel method expands the EDA analytical toolbox and may be useful in populations with highly variable basal SCL or when comparing groups with different basal SCL. Future research should test for reproducibility and generalizability in other tasks, samples, and contexts. IMPACT STATEMENTS: This article is important because it introduces a novel method to enhance sensitivity and statistical power in analyses of skin conductance responses from electrodermal data.

The Stability and Validity of Automated Indices of Vocal Development in Infants With Autistic and Non-Autistic Siblings

PURPOSE

This study evaluates the extent to which automated indices of vocal development are stable and valid for predicting language in infants at increased familial likelihood for autism and/or language impairment and relatively lower likelihood infants.

METHOD

A group of infants with autistic siblings (Sibs-autism; 20 infants) and a comparison group of infants with non-autistic siblings (Sibs-NA; 20 infants) wore Language ENvironment Analysis (LENA) recording devices for 16 hr on 2 days within a 1-week period. Extant software was used to derive several putative indices of vocal development from these recordings. Stability of these variables was examined across and within groups. Expressive and receptive language aggregates were calculated for each participant. Multiple regression analyses were used to (a) evaluate zero-order correlations for variables derived from LENA recordings with concurrent and future language and (b) test whether those associations were moderated by group status.

RESULTS

Both stability and validity differed by variable and group status. All variables reached acceptable stability in the Sibs-autism group within two to three observations, whereas stability of most variables was attenuated in the Sibs-NA group. No variables were associated with concurrent language in the theoretically motivated direction across groups, but two variables were strongly associated with concurrent expressive language in only the Sibs-NA group. Additionally, two variables were associated with later expressive language, though these correlations were again stronger in the Sibs-NA versus Sibs-autism group.

CONCLUSIONS

Although selected automated indices of vocal development were stable in Sibs-autism and/or valid for predicting expressive language within Sibs-NA, no scores showed strong, theoretically motivated associations with language within the Sibs-autism group. Automated indices of vocal development may, thus, have limited validity or clinical utility for predicting language development in infants at elevated familial likelihood for autism.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.24415735.

Say that again: Quantifying patterns of production for children with autism using recurrence analysis

The current research study characterized syntactic productivity across a range of 5-year-old children with autism and explored the degree to which this productivity was associated with standardized measures of language and autism symptomatology. Natural language samples were transcribed from play-based interactions between a clinician and participants with an autism diagnosis. Speech samples were parsed for grammatical morphemes and were used to generate measures of MLU and total number of utterances. We applied categorical recurrence quantification analysis, a technique used to quantify patterns of repetition in behaviors, to the children’s noun-related and verb-related speech. Recurrence metrics captured the degree to which children repeated specific lexical/grammatical units (i.e., recurrence rate) and the degree to which children repeated combinations of lexical/grammatical units (i.e., percent determinism). Findings indicated that beyond capturing patterns shown in traditional linguistic analysis, recurrence can reveal differences in the speech productions of children with autism spectrum disorder at the lexical and grammatical levels. We also found that the degree of repeating noun-related units and grammatical units was related to MLU and ADOS Severity Score, while the degree of repeating unit combinations (e.g., saying “the big fluffy dog” or the determiner-adjective-adjective-noun construction multiple times), in general, was only related to MLU.

Conversation Initiation of Mothers, Fathers, and Toddlers in their Natural Home Environment

In a conversational exchange, interlocutors use social cues including conversational turn-taking to communicate. There has been attention in the literature concerning how mothers, fathers, boys, and girls converse with each other, and in particular who initiates a conversation. Better understanding of conversational dynamics may deepen our understanding of social roles, speech and language development, and individual language variability. Here we use large-scale automatic analysis of 186 naturalistic daylong acoustic recordings to examine the conversational dynamics of 26 families with children about 30 months of age to better understand communication roles. Families included 15 with boys and 11 with girls. There was no difference in conversation initiation rate by child sex, but children initiated more conversations than mothers, and mothers initiated more than fathers. Results support developmental theories of the different and variable roles that interlocutors play in a social context.

Objective measurement of vocalizations in the assessment of autism spectrum disorder symptoms in preschool age children

Assessment of autism spectrum disorder (ASD) relies on expert clinician observation and judgment, but objective measurement tools have the potential to provide additional information on ASD symptom severity. Diagnostic evaluations for ASD typically include the autism diagnostic observation schedule (ADOS-2), a semi-structured assessment composed of a series of social presses. The current study examined associations between concurrent objective features of child vocalizations during the ADOS-2 and examiner-rated autism symptom severity. The sample included 66 children (49 male; M = 40 months, SD = 10.58) evaluated in a university-based clinic, 61 of whom received an ASD diagnosis. Research reliable administration of the ADOS-2 provided social affect (SA) and restricted and repetitive behavior (RRB) calibrated severity scores (CSS). Audio was recorded from examiner-worn eyeglasses during the ADOS-2 and child and adult speech were differentiated with LENA SP Hub. PRAAT was used to ascertain acoustic features of the audio signal, specifically the mean fundamental vocal frequency (F0) of LENA-identified child speech-like vocalizations (those with phonemic content), child cry vocalizations, and adult speech. Sphinx-4 was employed to estimate child and adult phonological features indexed by the average consonant and vowel count per vocalization. More than a quarter of the variance in ADOS-2 RRB CSS was predicted by the combination of child phoneme count per vocalization and child vocalization F0. Findings indicate that both acoustic and phonological features of child vocalizations are associated with expert clinician ratings of autism symptom severity. LAY SUMMARY: Determination of the severity of autism spectrum disorder is based in part on expert (but subjective) clinician observations during the ADOS-2. Two characteristics of child vocalizations-a smaller number of speech-like sounds per vocalization and higher pitched vocalizations (including cries)-were associated with greater autism symptom severity. The results suggest that objectively ascertained characteristics of children's vocalizations capture variance in children's restricted and repetitive behaviors that are reflected in clinician severity indices.

Vocal development in a large-scale crosslinguistic corpus

This study evaluates whether early vocalizations develop in similar ways in children across diverse cultural contexts. We analyze data from daylong audio recordings of 49 children (1-36 months) from five different language/cultural backgrounds. Citizen scientists annotated these recordings to determine if child vocalizations contained canonical transitions or not (e.g., "ba" vs. "ee"). Results revealed that the proportion of clips reported to contain canonical transitions increased with age. Furthermore, this proportion exceeded 0.15 by around 7 months, replicating and extending previous findings on canonical vocalization development but using data from the natural environments of a culturally and linguistically diverse sample. This work explores how crowdsourcing can be used to annotate corpora, helping establish developmental milestones relevant to multiple languages and cultures. Lower inter-annotator reliability on the crowdsourcing platform, relative to more traditional in-lab expert annotators, means that a larger number of unique annotators and/or annotations are required, and that crowdsourcing may not be a suitable method for more fine-grained annotation decisions. Audio clips used for this project are compiled into a large-scale infant vocalization corpus that is available for other researchers to use in future work.

Drug development for Autism Spectrum Disorder (ASD): Progress, challenges, and future directions

In 2017, facing lack of progress and failures encountered in targeted drug development for Autism Spectrum Disorder (ASD) and related neurodevelopmental disorders, the ISCTM with the ECNP created the ASD Working Group charged to identify barriers to progress and recommending research strategies for the field to gain traction. Working Group international academic, regulatory and industry representatives held multiple in-person meetings, teleconferences, and subgroup communications to gather a wide range of perspectives on lessons learned from extant studies, current challenges, and paths for fundamental advances in ASD therapeutics. This overview delineates the barriers identified, and outlines major goals for next generation biomedical intervention development in ASD. Current challenges for ASD research are many: heterogeneity, lack of validated biomarkers, need for improved endpoints, prioritizing molecular targets, comorbidities, and more. The Working Group emphasized cautious but unwavering optimism for therapeutic progress for ASD core features given advances in the basic neuroscience of ASD and related disorders. Leveraging genetic data, intermediate phenotypes, digital phenotyping, big database discovery, refined endpoints, and earlier intervention, the prospects for breakthrough treatments are substantial. Recommendations include new priorities for expanded research funding to overcome challenges in translational clinical ASD therapeutic research.

Validation of the Language ENvironment Analysis (LENA) system for Dutch

The validity of the Language ENvironment Analysis (LENA) System was evaluated for Dutch. 216 5-min samples (six samples per age per child) were selected from daylong recordings at 5, 10 and 14 months of age of native Dutch-speaking younger siblings of children with autism spectrum disorder (N = 6) and of typically developing children (N = 6). Two native Dutch-speaking coders counted the amount of adult words (AWC), child vocalisations (CVC) and conversational turns (CT). Consequently, correlations between LENA and human estimates were explored. Correlations were high for AWC at all ages (r = .73 to .81). Regarding CVC, estimates were moderately correlated at 5 months (r = .57) but the correlation decreased at 10 (r = .37) and 14 months (r = .14). Correlations for CT were low at all ages (r = .19 to .28). Lastly, correlations were not influenced by the risk status of the children.

Eliciting Language Samples for Analysis (ELSA): A New Protocol for Assessing Expressive Language and Communication in Autism

Expressive language and communication are among the key targets of interventions for individuals with autism spectrum disorder (ASD), and natural language samples provide an optimal approach for their assessment. Currently, there are no protocols for collecting such samples that cover a wide range of ages or language abilities, particularly for children/adolescents who have very limited spoken language. We introduce a new protocol for collecting language samples, eliciting language samples for analysis (ELSA), and a novel approach for deriving basic measures of verbal communicative competence from it that bypasses the need for time-consuming transcription. Study 1 presents ELSA-adolescents (ELSA-A), designed for minimally and low-verbal older children/adolescents with ASD. The protocol successfully engaged and elicited speech from 46 participants across a wide range of ages (6;6-19;7) with samples averaging 20-25 min. The collected samples were segmented into speaker utterances (examiner and participant) using real-time coding as one is listening to the audio recording and two measures were derived: frequency of utterances and conversational turns per minute. These measures were shown to be reliable and valid. For Study 2, ELSA was adapted for younger children (ELSA-Toddler [ELSA-T]) with samples averaging 29 min from 19 toddlers (2;8-4;10 years) with ASD. Again, measures of frequency of utterances and conversational turns derived from ELSA-T were shown to have strong psychometric properties. In Study 3, we found that ELSA-A and ELSA-T were equivalent in eliciting language from 17 children with ASD (ages: 4;0-6;8), demonstrating their suitability for deriving robust objective assessments of expressive language that could be used to track change in ability over time. We introduce a new protocol for collecting expressive language samples, ELSA, that can be used with a wide age range, from toddlers (ELSA-T) to older adolescents (ELSA-A) with ASD who have minimal or low-verbal abilities. The measures of language and communication derived from them, frequency of utterances, and conversational turns per minute, using real-time coding methods, can be used to characterize ability and chart change in intervention research. LAY SUMMARY: We introduce a new protocol for collecting expressive language samples, ELSA, that can be used with a wide age range, from toddlers (ELSA-T) to older adolescents (ELSA-A) with autism spectrum disorder who have minimal or low-verbal abilities. The measures of language and communication derived from them, frequency of utterances and conversational turns per minute, using real-time coding methods, can be used to characterize ability and chart change in intervention research.

Accuracy of the Language Environment Analysis System Segmentation and Metrics: A Systematic Review

Purpose The Language Environment Analysis (LENA) system provides automated measures facilitating clinical and nonclinical research and interventions on language development, but there are only a few, scattered independent reports of these measures' validity. The objectives of the current systematic review were to (a) discover studies comparing LENA output with manual annotation, namely, accuracy of talker labels, as well as involving adult word counts (AWCs), conversational turn counts (CTCs), and child vocalization counts (CVCs); (b) describe them qualitatively; (c) quantitatively integrate them to assess central tendencies; and (d) quantitatively integrate them to assess potential moderators. Method Searches on Google Scholar, PubMed, Scopus, and PsycInfo were combined with expert knowledge, and interarticle citations resulting in 238 records screened and 73 records whose full text was inspected. To be included, studies must target children under the age of 18 years and report on accuracy of LENA labels (e.g., precision and/or recall) and/or AWC, CTC, or CVC (correlations and/or error metrics). Results A total of 33 studies, in 28 articles, were discovered. A qualitative review revealed most validation studies had not been peer reviewed as such and failed to report key methodology and results. Quantitative integration of the results was possible for a broad definition of recall and precision (M = 59% and 68%, respectively; N = 12-13), for AWC (mean r = .79, N = 13), CVC (mean r = .77, N = 5), and CTC (mean r = .36, N = 6). Publication bias and moderators could not be assessed meta-analytically. Conclusion Further research and improved reporting are needed in studies evaluating LENA segmentation and quantification accuracy, with work investigating CTC being particularly urgent. Supplemental Material https://osf.io/4nhms/.

Pre- and Paralinguistic Vocal Production in ASD: Birth Through School Age

PURPOSE OF REVIEW

We review what is known about how pre-linguistic vocal differences in autism spectrum disorder (ASD) unfold across development and consider whether vocalization features can serve as useful diagnostic indicators.

RECENT FINDINGS

Differences in the frequency and acoustic quality of several vocalization types (e.g., babbles and cries) during the first year of life are associated with later ASD diagnosis. Paralinguistic features (e.g., prosody) measured during early and middle childhood can accurately classify current ASD diagnosis using cross-validated machine learning approaches. Pre-linguistic vocalization differences in infants are promising behavioral markers of later ASD diagnosis. In older children, paralinguistic features hold promise as diagnostic indicators as well as clinical targets. Future research efforts should focus on (1) bridging the gap between basic research and practical implementations of early vocalization-based risk assessment tools, and (2) demonstrating the clinical impact of targeting atypical vocalization features during social skill interventions for older children.