Soonshin Seo

Orcid: 0000-0002-1897-8256

According to our database1, Soonshin Seo authored at least 11 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Unified Speech-Text Pretraining for Spoken Dialog Modeling.
CoRR, 2024

2023
Encoder-decoder multimodal speaker change detection.
CoRR, 2023

2022
Convolutional Neural Networks Using Log Mel-Spectrogram Separation for Audio Event Classification with Unknown Devices.
J. Web Eng., 2022

Hybrid CTC-Attention Network-Based End-to-End Speech Recognition System for Korean Language.
J. Web Eng., 2022

Blank Collapse: Compressing CTC emission for the faster decoding.
CoRR, 2022

2021
Robustness of Differentiable Neural Computer Using Limited Retention Vector-based Memory Deallocation in Language Model.
KSII Trans. Internet Inf. Syst., 2021

Shallow Convolution-Augmented Transformer with Differentiable Neural Computer for Low-Complexity Classification of Variable-Length Acoustic Scene.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

2020
Self-Attentive Multi Layer Aggregation with Feature Recalibration and Normalization for End-to-End Speaker Verification System.
CoRR, 2020

Masked cross self-attention encoding for deep speaker embedding.
CoRR, 2020

2019
Shortcut Connections Based Deep Speaker Embeddings for End-to-End Speaker Verification System.
Proceedings of the Interspeech 2019, 2019

Environmental Noise Robustness for Korean Fricatives Using Speech Enhancement Generative Adversarial Networks.
Proceedings of the IEEE International Conference on Big Data and Smart Computing, 2019


  Loading...