Urmăriți
Kyu Jeong Han
Kyu Jeong Han
Amazon Web Services (AWS)
Adresă de e-mail confirmată pe amazon.com
Titlu
Citat de
Citat de
Anul
A review of speaker diarization: Recent advances with deep learning
TJ Park, N Kanda, D Dimitriadis, KJ Han, S Watanabe, S Narayanan
Computer Speech & Language 72, 101317, 2022
3942022
Automatic speaker age and gender recognition using acoustic and prosodic level information fusion
M Li, KJ Han, S Narayanan
Computer Speech & Language 27 (1), 151-167, 2013
2372013
Auto-tuning spectral clustering for speaker diarization using normalized maximum eigengap
TJ Park, KJ Han, M Kumar, S Narayanan
IEEE Signal Processing Letters 27, 381-385, 2019
1412019
E-branchformer: Branchformer with enhanced merging for speech recognition
K Kim, F Wu, Y Peng, J Pan, P Sridhar, KJ Han, S Watanabe
2022 IEEE Spoken Language Technology Workshop (SLT), 84-91, 2023
952023
The CAPIO 2017 conversational speech recognition system
KJ Han, A Chandrashekaran, J Kim, I Lane
arXiv preprint arXiv:1801.00059, 2017
902017
Strategies to improve the robustness of agglomerative hierarchical clustering under data source variation for speaker diarization
KJ Han, S Kim, SS Narayanan
IEEE Transactions on Audio, Speech, and Language Processing 16 (8), 1590-1601, 2008
812008
State-of-the-art speech recognition using multi-stream self-attention with dilated 1d convolutions
KJ Han, R Prieto, T Ma
2019 IEEE Automatic speech recognition and understanding workshop (ASRU), 54-61, 2019
782019
Slue: New benchmark tasks for spoken language understanding evaluation on natural speech
S Shon, A Pasad, F Wu, P Brusco, Y Artzi, K Livescu, KJ Han
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
752022
Robust language identification using convolutional neural network features.
S Ganapathy, KJ Han, S Thomas, MK Omar, M Van Segbroeck, ...
Interspeech, 1846-1850, 2014
682014
A robust stopping criterion for agglomerative hierarchical clustering in a speaker diarization system.
KJ Han, SS Narayanan
Interspeech, 1853-1856, 2007
592007
Multistream CNN for robust acoustic modeling
KJ Han, J Pan, VKN Tadala, T Ma, D Povey
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
512021
Combining five acoustic level modeling methods for automatic speaker age and gender recognition.
M Li, CS Jung, KJ Han
INTERSPEECH, 2826-2829, 2010
472010
Performance-efficiency trade-offs in unsupervised pre-training for speech recognition
F Wu, K Kim, J Pan, KJ Han, KQ Weinberger, Y Artzi
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
422022
Speaker diarization with lexical information
TJ Park, KJ Han, J Huang, X He, B Zhou, P Georgiou, S Narayanan
arXiv preprint arXiv:2004.06756, 2020
392020
Deep Learning-Based Telephony Speech Recognition in the Wild
KJ Han, S Hahm, BH Kim, J Kim, IR Lane
INTERSPEECH, 1323-1327, 2017
382017
ASAPP-ASR: Multistream CNN and self-attentive SRU for SOTA speech recognition
J Pan, J Shapiro, J Wohlwend, KJ Han, T Lei, T Ma
arXiv preprint arXiv:2005.10469, 2020
372020
Wav2seq: Pre-training speech-to-text encoder-decoder models using pseudo languages
F Wu, K Kim, S Watanabe, KJ Han, R McDonald, KQ Weinberger, Y Artzi
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
352023
Identifying a driver of a vehicle
SV Myers, S Elwart, WJ Talamonti, JT Mullen, ZD Nelson, T Smith, ...
US Patent 9,707,911, 2017
322017
Agglomerative hierarchical speaker clustering using incremental Gaussian mixture cluster modeling.
KJ Han, SS Narayanan
Interspeech, 20-23, 2008
292008
Novel inter-cluster distance measure combining GLR and ICR for improved agglomerative hierarchical speaker clustering
KJ Han, SS Narayanan
2008 IEEE International Conference on Acoustics, Speech and Signal …, 2008
222008
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20