62 citations · 116 across the 14 of their papers we have counts for
6 papers · 1 filter
Multi-speaker Emotional Text-to-speech Synthesizer
Sungjae Cho, Soo-Young Lee
We present a methodology to train our multi-speaker emotional text-to-speech synthesizer that can express speech for 10 speakers' 7 different emotions. All silences from audio samp…
Unigram-Normalized Perplexity as a Language Model Performance Measure with Different Vocabulary Sizes
Jihyeon Roh, Sang-Hoon Oh, Soo-Young Lee
Although Perplexity is a widely used performance metric for language models, the values are highly dependent upon the number of words in the corpus and is useful to compare perform…
Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models
Jihyeon Roh, Huiseong Gim, Soo-Young Lee
We report a GPT-based multi-sentence language model for dialogue generation and document understanding. First, we propose a hierarchical GPT which consists of three blocks, i.e., a…
Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
Geonmin Kim, Hwaran Lee, Bo-Kyeong Kim +2
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhance…
Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
Hwaran Lee, Geonmin Kim, Ho-Gyeong Kim +2
Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features. How…
Compositional Sentence Representation from Character within Large Context Text
Geonmin Kim, Hwaran Lee, Jisu Choi +1
This paper describes a Hierarchical Composition Recurrent Network (HCRN) consisting of a 3-level hierarchy of compositional models: character, word and sentence. This model is desi…