Eesung Kim

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 13

Top Topics

Language Understanding

Speech Recognition

Lexical Features

Joint Optimization

Top Venues

IEEE Signal Process. Lett.

Publications

Eesung Kim, Yun Tang, Taeyeon Ki, Divya Neelagiri, Vijendra Raj Apsingekar
Joint End-to-End Spoken Language Understanding and Automatic Speech Recognition Training Based on Unified Speech-to-Text Pre-Training. ICASSP (2024)
Eesung Kim, Aditya Jajodia, Cindy Tseng, Divya Neelagiri, Taeyeon Ki, Vijendra Raj Apsingekar
Efficient Adaptation of Spoken Language Understanding based on End-to-End Automatic Speech Recognition. INTERSPEECH (2023)
Eesung Kim, Jae-Jin Jeon, Hyeji Seo, Hoon Kim
Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning. CoRR (2022)
Eesung Kim, Jae-Jin Jeon, Hyeji Seo, Hoon Kim
Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning. INTERSPEECH (2022)
Dan Lim, Sunghee Jung, Eesung Kim
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech. CoRR (2022)
Dan Lim, Sunghee Jung, Eesung Kim
JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech. INTERSPEECH (2022)
Jae-Jin Jeon, Eesung Kim
Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition. ICASSP (2021)
Eesung Kim, Jae-Jin Jeon, Hyeji Seo
U-Convolution Based Residual Echo Suppression with Multiple Encoders. ICASSP (2021)
Eesung Kim, Hyeji Seo
SE-Conformer: Time-Domain Speech Enhancement Using Conformer. Interspeech (2021)
Jae-Jin Jeon, Eesung Kim
Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition. CoRR (2020)
Eesung Kim, Hyungchan Song, Jong Won Shin
Affective Latent Representation of Acoustic and Lexical Features for Emotion Recognition. Sensors 20 (9) (2020)
Juntae Kim, Yoonhan Lee, Eesung Kim
Accelerating RNN Transducer Inference via Adaptive Expansion Search. IEEE Signal Process. Lett. 27 (2020)
Eesung Kim, Jong Won Shin
DNN-based Emotion Recognition Based on Bottleneck Acoustic Features and Lexical Features. ICASSP (2019)