Graph-Aware Transformer: Is Attention All Graphs Need?

no code implementations • 9 Jun 2020 • Sanghyun Yoo, Young-Seok Kim, Kang Hyun Lee, Kuhwan Jeong, Junhwi Choi, Hoshik Lee, Young Sang Choi

To cover the broad range of graph-data applications including graph classification as well as graph generation, it is desirable to have a general and flexible model consisting of an encoder and a decoder that can handle graph data.

Graph Classification Graph Generation

Adaptable Multi-Domain Language Model for Transformer ASR

no code implementations • 14 Aug 2020 • Taewoo Lee, Min-Joong Lee, Tae Gyoon Kang, Seokyeoung Jung, Minseok Kwon, Yeona Hong, Jungin Lee, Kyoung-Gu Woo, Ho-Gyeong Kim, Jiseung Jeong, Ji-Hyun Lee, Hosik Lee, Young Sang Choi

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR.

Domain Adaptation Language Modelling

Learning Monotonic Alignments with Source-Aware GMM Attention

no code implementations • 1 Jan 2021 • Tae Gyoon Kang, Ho-Gyeong Kim, Min-Joong Lee, Jihyun Lee, Seongmin Ok, Hoshik Lee, Young Sang Choi

Transformers with soft attention have been widely adopted to various sequence-to-sequence tasks.

speech-recognition Speech Recognition

Towards Synthesizing Twelve-Lead Electrocardiograms from Two Asynchronous Leads

no code implementations • 28 Feb 2021 • Yong-Yeon Jo, Young Sang Choi, Jong-Hwan Jang, Joon-Myoung Kwon

The electrocardiogram (ECG) records electrical signals in a non-invasive way to observe the condition of the heart, typically looking at the heart from 12 different directions.

Data Augmentation Vocal Bursts Valence Prediction