Skip to content
conftrace_
2022 Interspeech INTERSPEECH 2022

A Deep Learning Platform for Language Education Research and Development

Abstract

We present a language education research, development, and deployment platform that allows researchers, developers and teachers alike to easily design pipelines and collaborate on components. We also show an example use case of our platform with components such as speech evaluation, question generation, and dialog systems. To our knowledge, this is the first language education research platform which supports the integration of speech, NLP, and various custom components.

Authors

Kye Min Tan, Richeng Duan, Xin Huang, Bowei Zou, Xuan Long Do

Topics

Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Transformers Deep Learning > Techniques > Pretraining

Keywords

transformer architecture question generation language education dialog system speech evaluation
Download PDF

More from Interspeech 2022

All Interspeech 2022 papers →
ELO-SPHERES intelligibility prediction model for the Clarity Prediction Challenge 2022
Listening with Googlears: Low-Latency Neural Multiframe Beamforming and Equalization for Hearing Aids
MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids
A VR Interactive 3D Mandarin Pronunciation Teaching Model
Squashed Weight Distribution for Low Bit Quantization of Deep Models
Evaluating the Performance of State-of-the-Art ASR Systems on Non-Native English using Corpora with Extensive Language Background Variation