Hong-Kwang Kuo — accepted AI-conference papers

2022

A New Data Augmentation Method for Intent Classification Enhancement and its Application on Spoken Conversation Datasets

Zvi Kons, Aharon Satt, Hong-Kwang Kuo, Samuel Thomas, Boaz Carmeli, Ron Hoory +1

ICASSP 2022accepted

Intent classifiers are vital to the successful operation of virtual agent systems. This is especially so in voice activated systems where the data can be noisy with many ambiguous directions for user intents. Before operation begins, these classifiers are generally lacking in real-world training dat…

Cited by 0 Source ↗Scholar ↗

2020

Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems

Yinghui Huang, Hong-Kwang Kuo, Samuel Thomas, Zvi Kons, Kartik Audhkhasi, Brian Kingsbury +2

ICASSP 2020accepted

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the S2I model with an ASR model trained on copious speech data can…

Cited by 0 Source ↗Scholar ↗