Knowledge distillation using output errors for self-attention end-to-end models HG Kim, H Na, H Lee, J Lee, TG Kang, MJ Lee, YS Choi ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 30 | 2019 |
Adaptable multi-domain language model for transformer asr T Lee, MJ Lee, TG Kang, S Jung, M Kwon, Y Hong, J Lee, KG Woo, ... ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 16 | 2021 |
Deep CNNs along the time axis with intermap pooling for robustness to spectral variations H Lee, G Kim, HG Kim, SH Oh, SY Lee IEEE Signal Processing Letters 23 (10), 1310-1314, 2016 | 11 | 2016 |
Partially overlapped inference for long-form speech recognition TG Kang, HG Kim, MJ Lee, J Lee, H Lee ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 7 | 2021 |
Multi-Domain Knowledge Distillation via Uncertainty-Matching for End-to-End ASR Models. HG Kim, MJ Lee, H Lee, TG Kang, J Lee, E Yang, SJ Hwang Interspeech, 2531-2535, 2021 | 5 | 2021 |
Rescoring of N-best hypotheses using top-down selective attention for automatic speech recognition HG Kim, H Lee, G Kim, SH Oh, SY Lee IEEE Signal Processing Letters 25 (2), 199-203, 2017 | 4 | 2017 |
Uncertainty measure for selective sampling based on class probability output networks HG Kim, RM Kil, SY Lee Neural Information Processing: 18th International Conference, ICONIP 2011 …, 2011 | 4 | 2011 |
Learning monotonic alignments with source-aware GMM attention TG Kang, HG Kim, MJ Lee, J Lee, S Ok, H Lee, YS Choi | 1 | 2021 |
Active learning for large-scale object classification: From exploration to exploitation HG Kim, J Roh, H Lee, G Kim, SY Lee Proceedings of the 3rd International Conference on Human-Agent Interaction …, 2015 | 1 | 2015 |
Active Learning by Selecting New Training Samples from Unlabelled Data HG Kim, CA Lee, SY Lee Biologically Inspired Cognitive Architectures 2012: Proceedings of the Third …, 2013 | | 2013 |