Foundational Research

Overview of LENA development and surprising findings, both confirming and expanding on Hart and Risley’s ground breaking work.

The current paper describes the Infoture Natural Language Study, an ongoing data collection effort designed to provide information about the language environment of infants and toddlers. Data collected contributes to product development and normative information for use with the LENA™ System. Study participants were representative of the US Census with respect to mothers’ attained education, and consisted of 314 normally developing infants and toddlers from monolingual English-speaking households living in the Denver-metro area. Participants provided day-long audio files of their natural language environment once a month, and certified speech language pathologists assessed participant language ability independently through standardized assessments. The resulting normative database contains over 18,000 hours of spontaneous speech data. This paper describes how normative information was derived for the Adult Word Count estimates (adult words spoken per day) and Conversational Turns estimates (adult-child alternations per day) that are reported in the LENA System.

The LENA™ language environment analysis system was designed to estimate adult and key child interactions in natural home environments. Contrary to controlled linguistic research environments, the speech used by the participants in this study was real, unrehearsed, and representative of each child’s typical daily language environment. In this paper, we describe the Audio Processing System in terms of information flow, feature extraction, and segmentation identification. We also reveal the audio specifications that were either met or exceeded during the development and design of the LENA digital language processor (DLP).

The LENA™ Digital Language Processor records real-time audio data that is transferred to a computer for processing by LENA language environment software V2.3.0. An Infoture Time Segment (ITS) file is created that summarizes information contained in the original audio file. To date, our focus has been estimating adult word counts and conversational turns between adult and key child. However, other audio factors are processed that have not yet been studied. Three versions of the LENA System exist: a consumer version; a clinician version; and a research version. The research version provides access to the ITS file. Here we describe the general content of the ITS file, detail the specific components, and discuss implications with regard to potential research goals.

The LENA™ language environment analysis system was designed to provide information about the language environment of infants and toddlers. In this technical report, we describe the reliability of the LENA System in terms of segmentation, adult word counts, and child vocalizations. We also describe unique sources of variability associated with data collection in the natural home environment.

Quantifying the accuracy and reliability of the LENA analysis software V2.3.0 is dependent on accurate and reliable transcription of the audio files by professional transcribers. Here, we disclose the analytical procedure designed and implemented by the Infoture transcription team to identify and code speakers. Very good inter-rater reliability was achieved between the criterion rater and seven secondary raters. Inter-rater reliability was assessed through segment classification agreement. Significant accuracy in the transcriptions provided by professional raters was critical to train the processing models used to automatically identify segments in the audio file and to subsequently test the accuracy and reliability of the segmentation process.

As part of the development of the LENA System, the research and development team at Infoture, consisting of speech language pathologists, linguists, statisticians and other researchers, created the LENA Developmental Snapshot (LDS). This 52-item Yes/No survey was designed to assess expressive and receptive language skills in children 2-36 months of age, and to estimate developmental age as a function of chronological age. Here we describe the development of the LDS. Initial respondents were drawn largely from the Infoture Natural Language Study participant pool, and their LDS scores were validated based on correlations with pre-existing standardized language and cognitive assessments. Participants in a longitudinal phase of the Infoture Natural Language Study completed the LDS at approximately monthly intervals to evaluate LDS test-retest reliability.