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 both teachers and classmates. Early childhood researchers recognize the importance in analyzing naturalistic vs. controlled lab recordings to measure both quality and quantity of child interactions. Recently, large language model-based speech technologies have performed well on conversational speech recognition. In this regard, we assess performance of such models on the wide dynamic scenario of early childhood classroom settings. This study investigates an alternate Deep Learning-based Teacher-Student learning solution for recognizing adult speech within preschool interactions. Our proposed adapted model achieves the best F1-score for recognizing most frequent 400 words on test sets for both classrooms. Additionally, F1-scores for alternate word groups provides a breakdown of performance across relevant language-based word-categories. 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 from this study can also be used for broad-based feedback for teachers.
more »
« less
Supporting Teacher Assessment in Chinese Language Learning Using Textual and Tonal Features
Assessment in the context of foreign language learning can be difficult and time-consuming for instructors. Distinctive from other domains, language learning often requires teachers to assess each student’s ability to speak the language, making this process even more time-consuming in large classrooms which are particularly common in post-secondary settings; considering that language instructors often assess students through assignments requiring recorded audio, a lack of tools to support such teachers makes providing individual feedback even more challenging. In this work, we seek to explore the development of tools to automatically assess audio responses within a college-level Chinese language-learning course. We build a model designed to grade student audio assignments with the purpose of incorporating such a model into tools focused on helping both teachers and students in real classrooms. Building upon our prior work which explored features extracted from audio, the goal of this work is to explore additional features derived from tone and speech recognition models to help assess students on two outcomes commonly observed in language learning classes: fluency and accuracy of speech. In addition to the exploration of features, this work explores the application of Siamese deep learning models for this assessment task. We find that models utilizing tonal features exhibit higher predictive performance of student fluency while text-based features derived from speech recognition models exhibit higher predictive performance of student accuracy of speech.
more »
« less
- Award ID(s):
- 1931419
- NSF-PAR ID:
- 10191712
- Date Published:
- Journal Name:
- Artificial Intelligence in Education. AIED 2020. Lecture Notes in Computer Science
- Volume:
- 12164
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present and evaluate a machine learning based system that automatically grades audios of students speaking a foreign language. The use of automated systems to aid the assessment of student performance holds great promise in augmenting the teacher’s ability to provide meaningful feedback and instruction to students. Teachers spend a significant amount of time grading student work and the use of these tools can save teachers a significant amount of time on their grading. This additional time could be used to give personalized attention to each student. Significant prior research has focused on the grading of closed-form problems, open-ended essays and textual content. However, little research has focused on audio content that is much more prevalent in language study education. In this paper, we explore the development of automated assessment tools for audio responses in a college-level Chinese language-learning course. We analyze several challenges faced while working with data of this type as well as the generation and extraction of features for the purpose of building machine learning models to aid in the assessment of student language learning.more » « less
-
We present and evaluate a machine learning based system that automatically grades audios of students speaking a foreign language. The use of automated systems to aid the assessment of student performance holds great promise in augmenting the teacher’s ability to provide meaningful feedback and instruction to students. Teachers spend a significant amount of time grading student work and the use of these tools can save teachers a significant amount of time on their grading. This additional time could be used to give personalized attention to each student. Significant prior research has focused on the grading of closed-form problems, open-ended essays and textual content. However, little research has focused on audio content that is much more prevalent in the language-study education. In this paper, we explore the development of automated assessment tools for audio responses in a college-level Chinese language-learning course. We analyze several challenges faced while working with data of this type as well as the generation and extraction of features for the purpose of building machine learning models to aid in the assessment of student language learning.more » « less
-
Collaboration is a 21st Century skill as well as an effective method for learning, so detection of collaboration is important for both assessment and instruction. Speech-based collaboration detection can be quite accurate but collecting the speech of students in classrooms can raise privacy issues. An alternative is to send only whether or not the student is speaking. That is, the speech signal is processed at the microphone by a voice activity detector before being transmitted to the collaboration detector. Because the transmitted signal is binary (1 = speaking, 0 = silence), this method mitigates privacy issues. However, it may harm the accuracy of collaboration detection. To find out how much harm is done, this study compared the relative effectiveness of collaboration detectors based either on the binary signal or high-quality audio. Pairs of students were asked to work together on solving complex math problems. Three qualitative levels of interactivity was distinguished: Interaction, Cooperation and Other. Human coders used richer data (several audio and video streams) to choose the code for each episode. Machine learning was used to induce a detector to assign a code for every episode based on the features. The binary-based collaboration detectors delivered only slightly less accuracy than collaboration detectors based on the high quality audio signal.more » « less
-
Evidence has shown that facilitating student-centered learning (SCL) in STEM classrooms enhances student learning and satisfaction [1]–[3]. However, despite increased support from educational and government bodies to incorporate SCL practices [1], minimal changes have been made in undergraduate STEM curriculum [4]. Faculty often teach as they were taught, relying heavily on traditional lecture-based teaching to disseminate knowledge [4]. Though some faculty express the desire to improve their teaching strategies, they feel limited by a lack of time, training, and incentives [4], [5]. To maximize student learning while minimizing instructor effort to change content, courses can be designed to incorporate simpler, less time-consuming SCL strategies that still have a positive impact on student experience. In this paper, we present one example of utilizing a variety of simple SCL strategies throughout the design and implementation of a 4-week long module. This module focused on introductory tissue engineering concepts and was designed to help students learn foundational knowledge within the field as well as develop critical technical skills. Further, the module sought to develop important professional skills such as problem-solving, teamwork, and communication. During module design and implementation, evidence-based SCL teaching strategies were applied to ensure students developed important knowledge and skills within the short timeframe. Lectures featured discussion-based active learning exercises to encourage student engagement and peer collaboration [6]–[8]. The module was designed using a situated perspective, acknowledging that knowing is inseparable from doing [9], and therefore each week, the material taught in the two lecture sessions was directly applied to that week’s lab to reinforce students’ conceptual knowledge through hands-on activities and experimental outcomes. Additionally, the majority of assignments served as formative assessments to motivate student performance while providing instructors with feedback to identify misconceptions and make real-time module improvements [10]–[12]. Students anonymously responded to pre- and post-module surveys, which focused on topics such as student motivation for enrolling in the module, module expectations, and prior experience. Students were also surveyed for student satisfaction, learning gains, and graduate student teaching team (GSTT) performance. Data suggests a high level of student satisfaction, as most students’ expectations were met, and often exceeded. Students reported developing a deeper understanding of the field of tissue engineering and learning many of the targeted basic lab skills. In addition to hands-on skills, students gained confidence to participate in research and an appreciation for interacting with and learning from peers. Finally, responses with respect to GSTT performance indicated a perceived emphasis on a learner-centered and knowledge/community-centered approaches over assessment-centeredness [13]. Overall, student feedback indicated that SCL teaching strategies can enhance student learning outcomes and experience, even over the short timeframe of this module. Student recommendations for module improvement focused primarily on modifying the lecture content and laboratory component of the module, and not on changing the teaching strategies employed. The success of this module exemplifies how instructors can implement similar strategies to increase student engagement and encourage in-depth discussions without drastically increasing instructor effort to re-format course content. Introduction.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
