no code implementations • 7 Oct 2021 • Namkyu Jung, Geonmin Kim, Han-Gyu Kim
In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model.
no code implementations • 6 Oct 2021 • Namkyu Jung, Geonmin Kim, Joon Son Chung
Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 14 Mar 2020 • Bo-Kyeong Kim, Sungjin Park, Geonmin Kim, Soo-Young Lee
We aim to separate the generative factors of data into two latent vectors in a variational autoencoder.
1 code implementation • 6 Nov 2018 • Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim, Sang-Hoon Oh, Soo-Young Lee
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator.
no code implementations • 10 Jun 2016 • Hwaran Lee, Geonmin Kim, Ho-Gyeong Kim, Sang-Hoon Oh, Soo-Young Lee
Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features.
no code implementations • 2 May 2016 • Geonmin Kim, Hwaran Lee, Jisu Choi, Soo-Young Lee
In the HCRN, word representations are built from characters, thus resolving the data-sparsity problem, and inter-sentence dependency is embedded into sentence representation at the level of sentence composition.