Suyoun Kim

Improving RNN Transducer Based ASR with Auxiliary Tasks

2021

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various …

The Study on the Direction of Retraining Program Design for Drama Teaching Experts – A Case of Busan Metropolitan City –

2022 · 연극교육연구

우리나라 문화예술교육은 양적인 급성장을 거듭하여 왔다. 그리고 이제 질적 제고에 대한 담론들이 형 성되고 있는 실정이다. 그렇기에 질적 향상을 불러오는 데 결정적으로 기여하는 현장 전문가의 전문성 향상에 대한 관심이 지속될 수밖에 없다. 특히 2016년 이후 …

PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding

2024

Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution.Previous works have explored end-to-end models to improve the quality and robustness of SLU …

Joint CTC-attention based end-to-end speech recognition using multi-task learning

2017

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping between variable-length input …