51 citations · 157 across the 17 of their papers we have counts for
20 papers
Kosp2e: Korean Speech to English Translation Corpus
Won Ik Cho, Seok Min Kim, Hyunchang Cho +1
Most speech-to-text (S2T) translation studies use English speech as a source, which makes it difficult for non-English speakers to take advantage of the S2T technologies. For some…
Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
Myeonghun Jeong, Hyeongju Kim, Sung Jun Cheon +2
Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness…
Expressive Text-to-Speech using Style Tag
Minchan Kim, Sung Jun Cheon, Byoung Jin Choi +2
As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To…
StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands
Won Ik Cho, Sangwhan Moon, Jong In Kim +2
Paraphrasing is often performed with less concern for controlled style conversion. Especially for questions and commands, style-variant paraphrasing can be crucial in tone and mann…
Continuous Monitoring of Blood Pressure with Evidential Regression
Hyeongju Kim, Woo Hyun Kang, Hyeonseung Lee +1
Photoplethysmogram (PPG) signal-based blood pressure (BP) estimation is a promising candidate for modern BP measurements, as PPG signals can be easily obtained from wearable device…
Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning
Sung Hwan Mun, Woo Hyun Kang, Min Hyun Han +1
In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty…
Robust Text-Dependent Speaker Verification via Character-Level Information Preservation for the SdSV Challenge 2020
Sung Hwan Mun, Woo Hyun Kang, Min Hyun Han +1
This paper describes our submission to Task 1 of the Short-duration Speaker Verification (SdSV) challenge 2020. Task 1 is a text-dependent speaker verification task, where both the…
Disentangled speaker and nuisance attribute embedding for robust speaker verification
Woo Hyun Kang, Sung Hwan Mun, Min Hyun Han +1
Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the cl…
TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition
Ji Won Yoon, Hyeonseung Lee, Hyung Yong Kim +2
In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promisi…
WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang +3
In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teach…
Gated Recurrent Context: Softmax-free Attention for Online Encoder-Decoder Speech Recognition
Hyeonseung Lee, Woo Hyun Kang, Sung Jun Cheon +2
Recently, attention-based encoder-decoder (AED) models have shown state-of-the-art performance in automatic speech recognition (ASR). As the original AED models with global attenti…
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
Hyeongju Kim, Hyeonseung Lee, Woo Hyun Kang +2
Flow-based generative models are composed of invertible transformations between two random variables of the same dimension. Therefore, flow-based models cannot be adequately traine…
Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation
Won Ik Cho, Donghyun Kwak, Ji Won Yoon +1
Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome proce…
Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives
Won Ik Cho, Young Ki Moon, Sangwhan Moon +2
Modern dialog managers face the challenge of having to fulfill human-level conversational skills as part of common user expectations, including but not limited to discourse with no…
Text Matters but Speech Influences: A Computational Analysis of Syntactic Ambiguity Resolution
Won Ik Cho, Jeonghwa Cho, Woo Hyun Kang +1
Analyzing how human beings resolve syntactic ambiguity has long been an issue of interest in the field of linguistics. It is, at the same time, one of the most challenging issues f…
On Measuring Gender Bias in Translation of Gender-neutral Pronouns
Won Ik Cho, Ji Won Kim, Seok Min Kim +1
Ethics regarding social bias has recently thrown striking issues in natural language processing. Especially for gender-related topics, the need for a system that reduces the model…
Investigating an Effective Character-level Embedding in Korean Sentence Classification
Won Ik Cho, Seok Min Kim, Nam Soo Kim
Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition. For such cases…
Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
Won Ik Cho, Hyeon Seung Lee, Ji Won Yoon +2
For a large portion of real-life utterances, the intention cannot be solely decided by either their semantic or syntactic characteristics. Although not all the sociolinguistic and…
Giving Space to Your Message: Assistive Word Segmentation for the Electronic Typing of Digital Minorities
Won Ik Cho, Sung Jun Cheon, Woo Hyun Kang +2
For readability and disambiguation of the written text, appropriate word segmentation is recommended for documentation, and it also holds for the digitized texts. If the language i…
Extracting Arguments from Korean Question and Command: An Annotated Corpus for Structured Paraphrasing
Won Ik Cho, Young Ki Moon, Woo Hyun Kang +1
Intention identification is a core issue in dialog management. However, due to the non-canonicality of the spoken language, it is difficult to extract the content automatically fro…