Automated classification of classroom climate by audio analysis
While in training, teachers are often given feedback about their teaching style by experts who observe the classroom. Trained observer coding of classroom such as the Classroom Assessment Scoring System (CLASS) provides valuable feedback to teachers, but the turnover time for observing and coding ma...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/88334 http://hdl.handle.net/10220/49458 |
| _version_ | 1811688402897076224 |
|---|---|
| author | James, Anusha Chua, Victoria Yi Han Maszczyk, Tomasz Núñez, Ana Moreno Bull, Rebecca Lee, Kerry Dauwels, Justin |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering James, Anusha Chua, Victoria Yi Han Maszczyk, Tomasz Núñez, Ana Moreno Bull, Rebecca Lee, Kerry Dauwels, Justin |
| author_sort | James, Anusha |
| collection | NTU |
| description | While in training, teachers are often given feedback about their teaching style by experts who observe the classroom. Trained observer coding of classroom such as the Classroom Assessment Scoring System (CLASS) provides valuable feedback to teachers, but the turnover time for observing and coding makes it hard to generate instant feedback. We aim to design technological platforms that analyze real-life data in learning environments, and generate automatic objective assessments in real-time. To this end, we adopted state-of- the-art speech processing technologies and conducted trials in real-life teaching environments. Although much attention has been devoted to speech processing for numerous applications, few researchers have attempted to apply speech processing for analyzing activities in classrooms. To address this shortcoming, we developed speech processing algorithms that detect speakers and social behavior from audio recordings in classrooms. Specifically, we aim to infer the climate in the classroom from non-verbal speech cues. We extract non-verbal speech cues and lowlevel audio features from speech segments and we train classifiers based on those cues. We were able to distinguish between positive and negative CLASS climate scores with 70-80% accuracy (estimated by leave-one-out crossvalidation). The results indicate the potential of predicting classroom climate automatically from audio recordings. |
| first_indexed | 2024-10-01T05:31:39Z |
| format | Conference Paper |
| id | ntu-10356/88334 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:31:39Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/883342019-12-06T17:00:58Z Automated classification of classroom climate by audio analysis James, Anusha Chua, Victoria Yi Han Maszczyk, Tomasz Núñez, Ana Moreno Bull, Rebecca Lee, Kerry Dauwels, Justin School of Electrical and Electronic Engineering International Workshop on Spoken Dialog System Technology Automated Classification Engineering::Electrical and electronic engineering Audio Analysis While in training, teachers are often given feedback about their teaching style by experts who observe the classroom. Trained observer coding of classroom such as the Classroom Assessment Scoring System (CLASS) provides valuable feedback to teachers, but the turnover time for observing and coding makes it hard to generate instant feedback. We aim to design technological platforms that analyze real-life data in learning environments, and generate automatic objective assessments in real-time. To this end, we adopted state-of- the-art speech processing technologies and conducted trials in real-life teaching environments. Although much attention has been devoted to speech processing for numerous applications, few researchers have attempted to apply speech processing for analyzing activities in classrooms. To address this shortcoming, we developed speech processing algorithms that detect speakers and social behavior from audio recordings in classrooms. Specifically, we aim to infer the climate in the classroom from non-verbal speech cues. We extract non-verbal speech cues and lowlevel audio features from speech segments and we train classifiers based on those cues. We were able to distinguish between positive and negative CLASS climate scores with 70-80% accuracy (estimated by leave-one-out crossvalidation). The results indicate the potential of predicting classroom climate automatically from audio recordings. Accepted version 2019-07-24T05:23:44Z 2019-12-06T17:00:58Z 2019-07-24T05:23:44Z 2019-12-06T17:00:58Z 2018-05-01 2018 Conference Paper James, A., Chua, V. Y. H., Maszczyk, T., Núñez, A. M., Bull, R., Lee, K., & Dauwels, J. (2018). Automated classification of classroom climate by audio analysis. International Workshop on Spoken Dialog System Technology. https://hdl.handle.net/10356/88334 http://hdl.handle.net/10220/49458 203830 en © 2018 The Author(s). All rights reserved. This paper was published by IWSDS 2018 in International Workshop on Spoken Dialog System Technology and is made available with permission of The Author(s). 8 p. application/pdf |
| spellingShingle | Automated Classification Engineering::Electrical and electronic engineering Audio Analysis James, Anusha Chua, Victoria Yi Han Maszczyk, Tomasz Núñez, Ana Moreno Bull, Rebecca Lee, Kerry Dauwels, Justin Automated classification of classroom climate by audio analysis |
| title | Automated classification of classroom climate by audio analysis |
| title_full | Automated classification of classroom climate by audio analysis |
| title_fullStr | Automated classification of classroom climate by audio analysis |
| title_full_unstemmed | Automated classification of classroom climate by audio analysis |
| title_short | Automated classification of classroom climate by audio analysis |
| title_sort | automated classification of classroom climate by audio analysis |
| topic | Automated Classification Engineering::Electrical and electronic engineering Audio Analysis |
| url | https://hdl.handle.net/10356/88334 http://hdl.handle.net/10220/49458 |
| work_keys_str_mv | AT jamesanusha automatedclassificationofclassroomclimatebyaudioanalysis AT chuavictoriayihan automatedclassificationofclassroomclimatebyaudioanalysis AT maszczyktomasz automatedclassificationofclassroomclimatebyaudioanalysis AT nunezanamoreno automatedclassificationofclassroomclimatebyaudioanalysis AT bullrebecca automatedclassificationofclassroomclimatebyaudioanalysis AT leekerry automatedclassificationofclassroomclimatebyaudioanalysis AT dauwelsjustin automatedclassificationofclassroomclimatebyaudioanalysis |