More Like this

1. Child vs Adult Speaker Diarization of naturalistic audio recordings in preschool environment using Deep Neural Networks

   Kothalkar, P. ; Hansen, J.H.L. ; Buzhardt, J. ; Irvin, D. ; Rous, B. ( March 2021 , ASEE 2021 Gulf-Southwest Annual Conference)

   null (Ed.)

   Speech and language development in children is crucial for ensuring optimal outcomes in their long term development and life-long educational journey. A child’s vocabulary size at the time of kindergarten entry is an early indicator of learning to read and potential long-term success in school. The preschool classroom is thus a promising venue for monitoring growth in young children by measuring their interactions with teachers and classmates. Automatic Speech Recognition (ASR) technologies provide the ability for ‘Early Childhood’ researchers for automatically analyzing naturalistic recordings in these settings. For this purpose, data are collected in a high-quality childcare center in the United States using Language Environment Analysis (LENA) devices worn by the preschool children. A preliminary task for ASR of daylong audio recordings would involve diarization, i.e., segmenting speech into smaller parts for identifying ‘who spoke when.’ This study investigates a Deep Learning-based diarization system for classroom interactions of 3-5-year-old children. However, the focus is on ’speaker group’ diarization, which includes classifying speech segments as being from adults or children from across multiple classrooms. SincNet based diarization systems achieve utterance level Diarization Error Rate of 19.1%. Utterance level speaker group confusion matrices also show promising, balanced results. These diarization systems have potential applications in developing metrics for adult-to-child or child-to-child rapid conversational turns in a naturalistic noisy early childhood setting. Such technical advancements will also help teachers better and more efficiently quantify and understand their interactions with children, make changes as needed, and monitor the impact of those changes. 

   more » « less
2. Measuring Frequency of Child-directed WH-Question Words for Alternate Preschool Locations using Speech Recognition and Location Tracking Technologies

   https://doi.org/10.1145/3461615.3485440  

   Kothalkar, P. ; Datla, S. ; Dutta, S. ; Hansen, J.H.L. ; Seven, Y. ; Irvin, D. ; Buzhardt J. ( October 2021 , ACM ICMI - WoCBU-2021: Workshop on Bridging Social Sciences and AI for Understanding Child Behavior)

   Speech and language development in children are crucial for ensuring effective skills in their long-term learning ability. A child’s vocabulary size at the time of entry into kindergarten is an early indicator of their learning ability to read and potential long-term success in school. The preschool classroom is thus a promising venue for assessing growth in young children by measuring their interactions with teachers as well as classmates. However, to date limited studies have explored such naturalistic audio communications. Automatic Speech Recognition (ASR) technologies provide an opportunity for ’Early Childhood’ researchers to obtain knowledge through automatic analysis of naturalistic classroom recordings in measuring such interactions. For this purpose, 208 hours of audio recordings across 48 daylong sessions are collected in a childcare learning center in the United States using Language Environment Analysis (LENA) devices worn by the preschool children. Approximately 29 hours of adult speech and 26 hours of child speech is segmented using manual transcriptions provided by CRSS transcription team. Traditional as well as End-to-End ASR models are trained on adult/child speech data subset. Factorized Time Delay Neural Network provides a best Word-Error-Rate (WER) of 35.05% on the adult subset of the test set. End-to-End transformer models achieve 63.5% WER on the child subset of the test data. Next, bar plots demonstrating the frequency of WH-question words in Science vs. Reading activity areas of the preschool are presented for sessions in the test set. It is suggested that learning spaces could be configured to encourage greater adult-child conversational engagement given such speech/audio assessment strategies. 

   more » « less
3. Capturing talk and proximity in the classroom: Advances in measuring features of young children’s friendships

   https://doi.org/10.1016/j.ecresq.2021.05.003  

   Irvin, D. W. ( January 2021 , Early childhood research quarterly)

   Young children’s friendships fuel essential developmental outcomes (e.g., social-emotional competence) and are thought to provide even greater benefits to children with or at-risk for disabilities. Teacher and parent report and sociometric measures are commonly used to measure friendships, and ecobehavioral assessment has been used to capture its features on a momentary basis. In this proof-of-concept study, we use Ubisense, the Language ENvironmental Analysis (LENA) recorder, and advanced speech processing algorithms to capture features of friendship –child-peer speech and proximity within activity areas . We collected 12,332 1-second speech and location data points. Our preliminary results indicate the focal child at-risk for a disability and each playmate spent time vocalizing near one another across 4 activity areas. Additionally, compared to the Blocks activity area, the children had significantly lower odds of talking while in proximity during Manipulatives and Science. This suggests that the activity areas children occupy may affect their engagement with peers and, in turn, the friendships they development. The proposed approach is a groundbreaking advance to understanding and supporting children’s friendships. 

   more » « less
4. Multimodal Approach for Assessing Neuromotor Coordination in Schizophrenia Using Convolutional Neural Networks

   https://doi.org/10.1145/3462244.3479967  

   Siriwardena, Yashish M. ; Espy-Wilson, Carol ; Kitchen, Chris ; Kelly, Deanna L. ( October 2021 , Proceedings of the 2021 International Conference on Multimodal Interaction (ICMI ’21))

   This study investigates the speech articulatory coordination in schizophrenia subjects exhibiting strong positive symptoms (e.g. hallucinations and delusions), using two distinct channel-delay correlation methods. We show that the schizophrenic subjects with strong positive symptoms and who are markedly ill pose complex articulatory coordination pattern in facial and speech gestures than what is observed in healthy subjects. This distinction in speech coordination pattern is used to train a multimodal convolutional neural network (CNN) which uses video and audio data during speech to distinguish schizophrenic patients with strong positive symptoms from healthy subjects. We also show that the vocal tract variables (TVs) which correspond to place of articulation and glottal source outperform the Mel-frequency Cepstral Coefficients (MFCCs) when fused with Facial Action Units (FAUs) in the proposed multimodal network. For the clinical dataset we collected, our best performing multimodal network improves the mean F1 score for detecting schizophrenia by around 18% with respect to the full vocal tract coordination (FVTC) baseline method implemented with fusing FAUs and MFCCs. 

   more » « less
5. End-to-end Child-Adult Speech Diarization in naturalistic conditions of preschool classrooms using room-independent ResNet model

   Kothalkar, P.V. ( May 2023 , The Journal of the Acoustical Society of America (submitted))

   Speech and language development are early indicators of overall analytical and learning ability in children. The preschool classroom is a rich language environment for monitoring and ensuring growth in young children by measuring their vocal interactions with teachers and classmates. Early childhood researchers are naturally interested in analyzing naturalistic vs. controlled lab recordings to measure both quality and quantity of such interactions. Unfortunately, present-day speech technologies are not capable of addressing the wide dynamic scenario of early childhood classroom settings. Due to the diversity of acoustic events/conditions in such daylong audio streams, automated speaker diarization technology would need to be advanced to address this challenging domain for segmenting audio as well as information extraction. This study investigates an alternate Deep Learning-based diarization solution for segmenting classroom interactions of 3-5 year old children with teachers. In this context, the focus on speech-type diarization which classifies speech segments as being either from adults or children partitioned across multiple classrooms. Our proposed ResNet model achieves a best F1-score of ∼78.0% on data from two classrooms, based on dev and test sets of each classroom. It is utilized with Automatic Speech Recognition-based resegmentation modules to perform child-adult diarization. Additionally, F1-scores are obtained for individual segments with corresponding speaker tags (e.g., adult vs. child), which provide knowledge for educators on child engagement through naturalistic communications. The study demonstrates the prospects of addressing educational assessment needs through communication audio stream analysis, while maintaining both security and privacy of all children and adults. The resulting child communication metrics have been used for broad-based feedback for teachers with the help of visualizations. 

   more » « less