Soonshin Seo

14 papers A* 1A 4Journal 8Unranked 1
YearRankTypeTitle / Venue / Authors
2024 A* conf
Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation.
NeurIPS
Heeseung Kim, Soonshin Seo, Kyeongseok Jeong, Ohsung Kwon, Soyoon Kim, Jungwhan Kim, Jaehong Lee, Eunwoo Song, Myungwoo Oh, Jung-Woo Ha, Sungroh Yoon, Kang Min Yoo
2024 J jnl
Unified Speech-Text Pretraining for Spoken Dialog Modeling.
CoRR
Heeseung Kim, Soonshin Seo, Kyeongseok Jeong, Ohsung Kwon, Jungwhan Kim, Jaehong Lee, Eunwoo Song, Myungwoo Oh, Sungroh Yoon, Kang Min Yoo
2023 A conf
Blank Collapse: Compressing CTC Emission for the Faster Decoding.
INTERSPEECH
Minkyu Jung, Ohhyeok Kwon, Seunghyun Seo, Soonshin Seo
2023 A conf
Encoder-decoder Multimodal Speaker Change Detection.
INTERSPEECH
Jee-weon Jung, Soonshin Seo, Hee-Soo Heo, Geonmin Kim, You Jin Kim, Youngki Kwon, Minjae Lee, Bong-Jin Lee
2023 J jnl
Encoder-decoder multimodal speaker change detection.
CoRR
Jee-weon Jung, Soonshin Seo, Hee-Soo Heo, Geonmin Kim, You Jin Kim, Youngki Kwon, Minjae Lee, Bong-Jin Lee
2022 J jnl
Blank Collapse: Compressing CTC emission for the faster decoding.
CoRR
Minkyu Jung, Ohhyeok Kwon, Seunghyun Seo, Soonshin Seo
2022 J jnl
Convolutional Neural Networks Using Log Mel-Spectrogram Separation for Audio Event Classification with Unknown Devices.
J. Web Eng.
Soonshin Seo, Changmin Kim, Ji-Hwan Kim
2022 J jnl
Hybrid CTC-Attention Network-Based End-to-End Speech Recognition System for Korean Language.
J. Web Eng.
Hosung Park, Changmin Kim, Hyunsoo Son, Soonshin Seo, Ji-Hwan Kim
2021 J jnl
Robustness of Differentiable Neural Computer Using Limited Retention Vector-based Memory Deallocation in Language Model.
KSII Trans. Internet Inf. Syst.
Donghyun Lee, Hosung Park, Soonshin Seo, Hyunsoo Son, Gyujin Kim, Ji-Hwan Kim
2021 A conf
Shallow Convolution-Augmented Transformer with Differentiable Neural Computer for Low-Complexity Classification of Variable-Length Acoustic Scene.
Interspeech
Soonshin Seo, Donghyun Lee, Ji-Hwan Kim
2020 J jnl
Masked cross self-attention encoding for deep speaker embedding.
CoRR
Soonshin Seo, Daniel Jun Rim, Junseok Oh, Ji-Hwan Kim
2020 J jnl
Self-Attentive Multi Layer Aggregation with Feature Recalibration and Normalization for End-to-End Speaker Verification System.
CoRR
Soonshin Seo, Ji-Hwan Kim
2019 — conf
Environmental Noise Robustness for Korean Fricatives Using Speech Enhancement Generative Adversarial Networks.
BigComp
Soonshin Seo, Minkyu Lim, Donghyun Lee, Hosung Park, Junseok Oh, Daniel Jun Rim, Ji-Hwan Kim
2019 A conf
Shortcut Connections Based Deep Speaker Embeddings for End-to-End Speaker Verification System.
INTERSPEECH
Soonshin Seo, Daniel Jun Rim, Minkyu Lim, Donghyun Lee, Hosung Park, Junseok Oh, Changmin Kim, Ji-Hwan Kim