Get started
Author

Soonshin Seo

Observed name: Seo, Soonshin
ORCID: 0000-0002-1897-8256
Observed ORCID: 0000-0002-1897-8256
OpenAlex ID: A5025853956
Shortcut Connections Based Deep Speaker Embeddings for End-to-End Speaker Verification System
2019 · Soonshin Seo, Daniel Jun Rim, et al. · Interspeech (USB) · 27
Convolutional Neural Networks Using Log Mel-Spectrogram Separation for Audio Event Classification with Unknown Devices
2022 · Soonshin Seo, Changmin Kim, et al. · Journal of Web Engineering · 26
PDF
HyperCLOVA X Technical Report
2024 · Yoo, Kang Min, Han, Jaegeun, et al. · arXiv (Cornell University) · 8
PDF
Korean Grapheme Unit-based Speech Recognition Using Attention-CTC Ensemble Network
2019 · Hosung Park, Soonshin Seo, et al. · International Symposium on Multimedia and Communication Technology (ISMAC) · 7
Shallow Convolution-Augmented Transformer with Differentiable Neural Computer for Low-Complexity Classification of Variable-Length Acoustic Scene
2021 · Soonshin Seo, Donghyun Lee, et al. · Interspeech (USB) · 6
Hybrid CTC-Attention Network-Based End-to-End Speech Recognition System for Korean Language
2022 · Hosung Park, Changmin Kim, et al. · Journal of Web Engineering · 5
PDF
Encoder-decoder Multimodal Speaker Change Detection
2023 · Jee-weon Jung, Soonshin Seo, et al. · Interspeech (USB) · 4
PDF
Language Model Using Differentiable Neural Computer Based on Forget Gate-Based Memory Deallocation
2021 · Donghyun Lee, Hosung Park, et al. · Computers, materials & continua/Computers, materials & continua (Print) · 4
Self-Attentive Multi-Layer Aggregation with Feature Recalibration and Deep Length Normalization for Text-Independent Speaker Verification System
2020 · Soonshin Seo, Ji-Hwan Kim · Electronics · 4
PDF
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
2024 · Heeseung Kim, Soonshin Seo, et al. · neural information processing systems · 3
PDF
Blank Collapse: Compressing CTC Emission for the Faster Decoding
2023 · Minkyu Jung, Ohhyeok Kwon, et al. · Interspeech (USB) · 3
PDF
Robustness of Differentiable Neural Computer Using Limited Retention Vector-based Memory Deallocation in Language Model
2021 · Donghyun Lee, Hosung Park, et al. · KSII Transactions on Internet and Information Systems · 3
Joint On-Demand Pruning and Online Distillation in Automatic Speech Recognition Language Model Optimization
2023 · Soonshin Seo, Ji-Hwan Kim · Computers, materials & continua/Computers, materials & continua (Print) · 2
PDF
TP-MobNet: A Two-pass Mobile Network for Low-complexity Classification of Acoustic Scene
2022 · Soonshin Seo, Junseok Oh, et al. · Computers, materials & continua/Computers, materials & continua (Print) · 1
Environmental Noise Robustness for Korean Fricatives Using Speech Enhancement Generative Adversarial Networks
2019 · Soonshin Seo, Minkyu Lim, et al. · IEEE International Conference on Big Data and Smart Computing (BigComp) · 1
Masked cross self-attentive encoding based speaker embedding for speaker verification
2020 · Soonshin Seo, Ji‐Hwan Kim · The Journal of the Acoustical Society of Korea
Self-Attentive Multi-Layer Aggregation with Feature Recalibration and Normalization for End-to-End Speaker Verification System
2020 · Seo, Soonshin, Kim, Ji-Hwan · arXiv (Cornell University)
PDF
Masked cross self-attention encoding for deep speaker embedding.
2020 · Soonshin Seo, Daniel Jun Rim, et al.
MCSAE: Masked Cross Self-Attentive Encoding for Speaker Embedding
2020 · Seo, Soonshin, Kim, Ji-Hwan · arXiv (Cornell University)
PDF
Hybrid CTC-Attention Based End-to-End Speech Recognition Using Korean Grapheme Unit
2018 · Ho-Sung Park, Dong‐Hyun Lee, et al. · Annual Conference on Human and Language Technology
Works count: 20
Citation count: 104
H-index: 5
I10-index: 2
Year
Topic
Type