Available here are the following materials: 1. A draft of the paper (not-final). *Evaluating the LENA systme for Korean_resubmit.pdf* 2. Manual for coding the 5 minute clips in Praat for the purpose of generating human-coded speaker identification and conversational turns to be compared with the LENA output. *LENA_Evaluation_Coding_Manual.pdf* 3. The manuscript referred to in (2), which describes transcription conventions for Korean mother-child interaction in the CHAT convention. *Ko_corpus_aug20.pdf* 4. A set of 60 Praat TextGrid files with human-coded labels based on the manual in (2). The text in the transcription is replaced with "x"'s to protect personal information of the participants. *Clips3_processed.zip* 5. A folder (*Correlations, acoustic analysis, figures*) which includes a script for generating the model for the acoustic analysis along with correlations and figures for AWC, CVC, and CTC analyses. Downloading the whole folder to run the script is recommended. Included in the folder are two data files (*F0_duration_measures.csv* and *LENA_Supplementary.xlsx*) necessary for running the script. The second of the two datafiles also includes supplementary variables about each clip that were not included in the main analysis (e.g. time of day of recording, day of the week of recording, exact age in days and weeks of child in each recording, etc). 6. A folder (*Interrater reliability*) including files and scripts used for interrater reliability analyses. Use the Read for instructions on how to run the scripts. Downloading the whole folder to run scripts is recommended. The folder includes: 1. Two zip files each with a set of 8 Praat TextGrid files coded by the original coder (Coder1) and a second coder (Coder2), which was used to calculate the inter-rater reliability. *Coder1_TextGrid.zip* and *Coder2_TextGrid.zip* 2. Two R scripts. One to process the TextGrids in the above textfile *Processing files for IRR.R*. And one to calculate interrater reliability variables. *Interrater Reliability.R* 3. Three CSV files necessary to run the second R script. This includes *Coder1.csv* and *Coder2.csv* which are the outputs of the first R script. And *OtherIRRVars.csv* which includes CTC and CVC counts from the two coders. 7. Link to the Github repository containing the data, Python script for calculating Recall & Precision, and other statistical analyses described in the paper. *https://github.com/terrykwon/lena_evaluation* The research was financially supported by a research fund from Chosun University in 2018 and Institute for Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (2019-0-01367, Infant-Mimic Neurocognitivive Developmental Machine Learning from Interaction Experience with Real World (BabyMind)).