Who Said What? An Automated Approach to Analyzing Speech in Preschool Classrooms

TL;DR

This study introduces an automated speech analysis framework for preschool classrooms using open source tools, enabling efficient classification and transcription of child and teacher speech to support language development research.

Contribution

It presents a novel automated framework combining speaker classification and transcription for preschool classroom recordings, validated against expert annotations.

Findings

Achieved 76% agreement with human expert in speaker classification.

Word error rate of 15% for transcriptions, comparable to human transcriptions.

Speech feature analysis showed consistency between automated and expert transcriptions.

Abstract

Young children spend substantial portions of their waking hours in noisy preschool classrooms. In these environments, children's vocal interactions with teachers are critical contributors to their language outcomes, but manually transcribing these interactions is prohibitive. Using audio from child- and teacher-worn recorders, we propose an automated framework that uses open source software both to classify speakers (ALICE) and to transcribe their utterances (Whisper). We compare results from our framework to those from a human expert for 110 minutes of classroom recordings, including 85 minutes from child-word microphones (n=4 children) and 25 minutes from teacher-worn microphones (n=2 teachers). The overall proportion of agreement, that is, the proportion of correctly classified teacher and child utterances, was .76, with an error-corrected kappa of .50 and a weighted F1 of .76. The word error rate for both teacher and child transcriptions was .15, meaning that 15% of words would need to be deleted, added, or changed to equate the Whisper and expert transcriptions. Moreover, speech features such as the mean length of utterances in words, the proportion of teacher and child utterances that were questions, and the proportion of utterances that were responded to within 2.5 seconds were similar when calculated separately from expert and automated transcriptions. The results suggest substantial progress in analyzing classroom speech that may support children's language development. Future research using natural language processing is under way to improve speaker classification and to analyze results from the application of the automated framework to a larger dataset containing classroom recordings from 13 children and 3 teachers observed on 17 occasions over one year.