A thorough evaluation of the Language Environment Analysis (LENATM) system

In the previous decade, dozens of studies involving thousands of children across several research disciplines have made use of a combined daylong audio-recorder and automated algorithmic analysis called the LENA^®^ system, which aims to assess children's language environment. While the system's prevalence in the language acquisition domain is steadily growing, there are only scattered validation efforts, on only some of its key characteristics. Here, we assess the LENA^®^ system's accuracy across all of its key measures: speaker classification, Child Vocalization Counts (CVC), Conversational Turn Counts (CTC), and Adult Word Counts (AWC). Our assessment is based on manual annotation of clips that have been randomly or periodically sampled out of daylong recordings, collected from (a) populations similar to the system's original training data (North American English-learning children aged 3-36 months), (b) children learning another dialect of English (UK), and (c) slightly older children growing up in a different linguistic and socio-cultural setting (Tsimane' learners in rural Bolivia). We find reasonably high accuracy in some measures (AWC, CVC), with more problematic levels of performance in others (CTC, precision of male adults and other children). Statistical analyses do not support the view that performance is worse for children who are dissimilar from the LENA^®^ original training set. Whether LENA^®^ results are accurate enough for a given research, educational, or clinical application depends largely on the specifics at hand. We therefore conclude with a set of recommendations to help researchers make this determination for their goals.

Download Full-text

Automated extraction of information from Language ENvironment Analysis (LENA) home recordings of older children with autism

The Journal of the Acoustical Society of America ◽

10.1121/1.4987356 ◽

2017 ◽

Vol 141 (5) ◽

pp. 3508-3508

Author(s):

Mark A. Clements ◽

Rahul Pawar ◽

Desmond Caulley ◽

Rebecca Jones ◽

Catherine Lord

Keyword(s):

Children With Autism ◽

Automated Extraction ◽

Older Children ◽

Environment Analysis ◽

Language Environment Analysis ◽

Language Environment

Download Full-text

Socioeconomic status correlates with measures of Language Environment Analysis (LENA) system: a meta-analysis

Journal of Child Language ◽

10.1017/s0305000921000441 ◽

2021 ◽

pp. 1-15

Author(s):

Leonardo PIOT ◽

Naomi HAVRON ◽

Alejandrina CRISTIA

Keyword(s):

Socioeconomic Status ◽

Meta Analysis ◽

Final Analysis ◽

Publication Type ◽

Environment Analysis ◽

System A ◽

Language Environment Analysis ◽

Language Environment ◽

Strength Of Association ◽

Important Evidence

Abstract Using a meta-analytic approach, we evaluate the association between socioeconomic status (SES) and children's experiences measured with the Language Environment Analysis (LENA) system. Our final analysis included 22 independent samples, representing data from 1583 children. A model controlling for LENATM measures, age and publication type revealed an effect size of r z = .186, indicating a small effect of SES on children's language experiences. The type of LENA metric measured emerged as a significant moderator, indicating stronger effects for adult word counts than child vocalization counts. These results provide important evidence for the strength of association between SES and children's everyday language experiences as measured with an unobtrusive recording analyzed automatically in a standardized fashion.

Download Full-text

Examining Factors Influencing the Viability of Automatic Acoustic Analysis of Child Speech

Journal of Speech Language and Hearing Research ◽

10.1044/2018_jslhr-s-17-0275 ◽

2018 ◽

Vol 61 (10) ◽

pp. 2487-2501 ◽

Cited By ~ 1

Author(s):

Thea Knowles ◽

Meghan Clayards ◽

Morgan Sonderegger

Keyword(s):

Young Children ◽

Acoustic Analysis ◽

Center Of Gravity ◽

Training Data ◽

Alignment Accuracy ◽

Older Children ◽

Acoustic Characteristics ◽

Phonetic Transcription ◽

Very Young Children ◽

Child Speech

Purpose Heterogeneous child speech was force-aligned to investigate whether (a) manipulating specific parameters could improve alignment accuracy and (b) forced alignment could be used to replicate published results on acoustic characteristics of /s/ production by children. Method In Part 1, child speech from 2 corpora was force-aligned with a trainable aligner (Prosodylab-Aligner) under different conditions that systematically manipulated input training data and the type of transcription used. Alignment accuracy was determined by comparing hand and automatic alignments as to how often they overlapped (%-Match) and absolute differences in duration and boundary placements. Using mixed-effects regression, accuracy was modeled as a function of alignment conditions, as well as segment and child age. In Part 2, forced alignments derived from a subset of the alignment conditions in Part 1 were used to extract spectral center of gravity of /s/ productions from young children. These findings were compared to published results that used manual alignments of the same data. Results Overall, the results of Part 1 demonstrated that using training data more similar to the data to be aligned as well as phonetic transcription led to improvements in alignment accuracy. Speech from older children was aligned more accurately than younger children. In Part 2, /s/ center of gravity extracted from force-aligned segments was found to diverge in the speech of male and female children, replicating the pattern found in previous work using manually aligned segments. This was true even for the least accurate forced alignment method. Conclusions Alignment accuracy of child speech can be improved by using more specific training and transcription. However, poor alignment accuracy was not found to impede acoustic analysis of /s/ produced by even very young children. Thus, forced alignment presents a useful tool for the analysis of child speech. Supplemental Material https://doi.org/10.23641/asha.7070105

Download Full-text

Accuracy of the Language Environment Analysis (LENA) speech processing system in identifying communicative vocalizations of young children and adults

The Journal of the Acoustical Society of America ◽

10.1121/10.0008584 ◽

2021 ◽

Vol 150 (4) ◽

pp. A358-A358

Author(s):

Laura Dilley ◽

Derek Houston

Keyword(s):

Young Children ◽

Speech Processing ◽

Processing System ◽

Environment Analysis ◽

Language Environment Analysis ◽

Language Environment

Download Full-text

Evaluating the Language ENvironment Analysis System for Korean

Journal of Speech Language and Hearing Research ◽

10.1044/2020_jslhr-20-00489 ◽

2021 ◽

Vol 64 (3) ◽

pp. 792-808

Author(s):

Margarethe McDonald ◽

Taeahn Kwon ◽

Hyunji Kim ◽

Youngki Lee ◽

Eon-Suk Ko

Keyword(s):

Error Rate ◽

English Language ◽

Word Count ◽

Data Set ◽

Environment Analysis ◽

Factors Affecting ◽

Identification Error ◽

Language Environment Analysis ◽

Language Environment ◽

Adult Word Count

Purpose The algorithm of the Language ENvironment Analysis (LENA) system for calculating language environment measures was trained on American English; thus, its validity with other languages cannot be assumed. This article evaluates the accuracy of the LENA system applied to Korean. Method We sampled sixty 5-min recording clips involving 38 key children aged 7–18 months from a larger data set. We establish the identification error rate, precision, and recall of LENA classification compared to human coders. We then examine the correlation between standard LENA measures of adult word count, child vocalization count, and conversational turn count and human counts of the same measures. Results Our identification error rate (64% or 67%), including false alarm, confusion, and misses, was similar to the rate found in Cristia, Lavechin, et al. (2020) . The correlation between LENA and human counts for adult word count ( r = .78 or .79) was similar to that found in the other studies, but the same measure for child vocalization count ( r = .34–.47) was lower than the value in Cristia, Lavechin, et al., though it fell within ranges found in other non-European languages. The correlation between LENA and human conversational turn count was not high ( r = .36–.47), similar to the findings in other studies. Conclusions LENA technology is similarly reliable for Korean language environments as it is for other non-English language environments. Factors affecting the accuracy of diarization include speakers' pitch, duration of utterances, age, and the presence of noise and electronic sounds.

Download Full-text

Facilitative Language Techniques Used in the Home by Caregivers of Young Children Who Are Deaf or Hard of Hearing

Perspectives of the ASHA Special Interest Groups ◽

10.1044/2021_persp-20-00297 ◽

2021 ◽

pp. 1-9

Author(s):

Aleah S. Brock ◽

Sandie M. Bass-Ringdahl

Keyword(s):

Young Children ◽

Natural Environment ◽

Hard Of Hearing ◽

Oral Communication ◽

Hearing Level ◽

Environment Analysis ◽

Hearing Devices ◽

Pilot Investigation ◽

Language Environment ◽

Adult Word Count

Purpose This research note reports preliminary data from an investigation of facilitative language techniques (FLTs) used in the natural environment by caregivers of children who are deaf or hard of hearing (DHH). The investigation seeks to establish a new method to collect and analyze data on caregiver FLT use in the home. Method This pilot investigation included two children under the age of 36 months with moderate-to-profound sensorineural hearing loss. Both children were consistent users of hearing devices and were pursing oral communication. Data were collected via the Language ENvironment Analysis (LENA) system in the participants' homes. Thirty-six 5-min segments containing the highest adult word count were extracted from each participant's sample. Researchers coded segments for the presence or absence of 10 FLTs within 30-s intervals. Results The collection, coding, and analysis of caregiver FLTs using LENA was a feasible method to investigate caregiver linguistic input in the natural environment. Despite differences in age, sex, and hearing level, the distribution of caregiver FLTs was similar for both participants. Caregivers used high levels of narration, closed-ended questions, and directives throughout the day. Conclusions Results of this investigation provide information about the types of FLTs that are used in the home by caregivers of young children who are DHH. Furthermore, results indicate the feasibility of this method to investigate in-home use of caregiver FLTs.

Download Full-text

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

Journal of Child Language ◽

10.1017/s0305000920000525 ◽

2020 ◽

pp. 1-27

Author(s):

Eva BRUYNEEL ◽

Ellen DEMURIE ◽

Sofie BOTERBERG ◽

Petra WARREYN ◽

Herbert ROEYERS

Keyword(s):

Autism Spectrum Disorder ◽

Children With Autism ◽

Autism Spectrum ◽

Typically Developing ◽

Typically Developing Children ◽

Risk Status ◽

Environment Analysis ◽

Language Environment Analysis ◽

Language Environment ◽

Conversational Turns

Abstract 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.

Download Full-text

Associations Between Maternal Stress, Early Language Behaviors, and Infant Electroencephalography During the First Year of Life

Journal of Child Language ◽

10.1017/s0305000920000501 ◽

2020 ◽

pp. 1-28

Author(s):

Lara J. PIERCE ◽

Emily REILLY ◽

Charles A. NELSON

Keyword(s):

Stressful Life Events ◽

Individual Variability ◽

First Year ◽

Early Language ◽

Environment Analysis ◽

High Exposure ◽

Gamma Power ◽

Language Environment ◽

First Year Of Life ◽

Conversational Turns

Abstract Associations have been observed between socioeconomic status (SES) and language outcomes from early childhood, but individual variability is high. Exposure to high levels of stress, often associated with low-SES status, might influence how parents and infants interact within the early language environment. Differences in these early language behaviors, and in early neurodevelopment, might underlie SES-based differences in language that emerge later on. Analysis of natural language samples from a predominantly low-/mid-income sample of mother-infant dyads, obtained using the Language Environment Analysis (LENA) system, found that maternal reports of exposure to stressful life events, and perceived stress, were negatively correlated with child vocalizations and conversational turns when infants were 6 and 12 months of age. Greater numbers of vocalizations and conversational turns were also associated with lower relative theta power and higher relative gamma power in 6- and 12-month baseline EEG – a pattern that might support subsequent language development.

Download Full-text