Zobrazeno 1 - 10
of 406
pro vyhledávání: '"Park, Tae Jin"'
Autor:
Park, Tae Jin, Huang, He, Jukic, Ante, Dhawan, Kunal, Puvvada, Krishna C., Koluguri, Nithin, Karpov, Nikolay, Laptev, Aleksandr, Balam, Jagadeesh, Ginsburg, Boris
Publikováno v:
CHiME-7 Workshop 2023
We present the NVIDIA NeMo team's multi-channel speech recognition system for the 7th CHiME Challenge Distant Automatic Speech Recognition (DASR) Task, focusing on the development of a multi-channel, multi-speaker speech recognition system tailored t
Externí odkaz:
http://arxiv.org/abs/2310.12378
Autor:
Park, Tae Jin, Huang, He, Hooper, Coleman, Koluguri, Nithin, Dhawan, Kunal, Jukic, Ante, Balam, Jagadeesh, Ginsburg, Boris
Publikováno v:
CHiME-7 Workshop 2023
We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap via the adj
Externí odkaz:
http://arxiv.org/abs/2310.12371
Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in hu
Externí odkaz:
http://arxiv.org/abs/2309.05248
Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way to cope w
Externí odkaz:
http://arxiv.org/abs/2203.15974
Autor:
Kang, Daeho, Jang, Heewon, Mok, Sori, Kim, Jun Yub, Choi, Younghun, Lee, Sun-Hong, Han, Sojeong, Park, Tae Jin, Moon, Hyo-Bang, Jeon, Junho
Publikováno v:
In Chemosphere November 2024 367
Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for either homogeneity or stationari
Externí odkaz:
http://arxiv.org/abs/2110.09695
Autor:
Lilja, Mathias, Leaback, Richard, Banefelt, Jonas, Park, Tae Jin, Shah, Darshini, Ferguson, William G., Friberg, Örjan
Publikováno v:
In JTCVS Open June 2024 19:116-130
Autor:
Park, Tae Jin, Kanda, Naoyuki, Dimitriadis, Dimitrios, Han, Kyu J., Watanabe, Shinji, Narayanan, Shrikanth
Speaker diarization is a task to label audio or video recordings with classes that correspond to speaker identity, or in short, a task to identify "who spoke when". In the early years, speaker diarization algorithms were developed for speech recognit
Externí odkaz:
http://arxiv.org/abs/2101.09624
Publikováno v:
In Journal of Hazardous Materials 5 January 2024 461
Autor:
Park, Tae-Jin1 (AUTHOR) etjpark@kaeri.re.kr, Kim, Ki-il2 (AUTHOR) kikim@cnu.ac.kr, Moon, Sangook3 (AUTHOR) smoon@mokwon.ac.kr
Publikováno v:
Sensors (14248220). Apr2024, Vol. 24 Issue 7, p2054. 17p.