Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Hee-Soo Heo"'
Publikováno v:
IEEE Access, Vol 8, Pp 166870-166879 (2020)
Common acoustic properties that different classes share degrades the performance of acoustic scene classification systems. This results in a phenomenon where a few confusing pairs of acoustic scenes dominate a significant proportion of all misclassif
Externí odkaz:
https://doaj.org/article/65973a18b4164f86a84ddf2022cd9446
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 16:1253-1262
Autor:
Jee-Weon Jung, Hee-Soo Heo, Bong-Jin Lee, Jaesung Huh, Andrew Brown, Youngki Kwon, Shinji Watanabe, Joon Son Chung
Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several challenges when adopting EEs for diarisation, from which we tackle two ke
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1ce3b6e15a3cdd06a97bc8c0a356b68
http://arxiv.org/abs/2210.14682
http://arxiv.org/abs/2210.14682
Autor:
Hye-jin Shim, Hemlata Tak, Xuechen Liu, Hee-Soo Heo, Jee-weon Jung, Joon Son Chung, Soo-Whan Chung, Ha-Jin Yu, Bong-Jin Lee, Massimiliano Todisco, Héctor Delgado, Kong Aik Lee, Md Sahidullah, Tomi Kinnunen, Nicholas Evans
Publikováno v:
Odyssey 2022-The Speaker and Language Recognition Workshop
Odyssey 2022-The Speaker and Language Recognition Workshop, Jun 2022, Beijing, China
Odyssey 2022-The Speaker and Language Recognition Workshop, Jun 2022, Beijing, China
Deep learning has brought impressive progress in the study of both automatic speaker verification (ASV) and spoofing countermeasures (CM). Although solutions are mutually dependent, they have typically evolved as standalone sub-systems whereby CM sol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4807a8147c4a95135bc271fb3a3291a6
http://arxiv.org/abs/2204.09976
http://arxiv.org/abs/2204.09976
In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts, which demons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f561d86ce89810aa3ce04b14088b0f44
http://arxiv.org/abs/2203.08488
http://arxiv.org/abs/2203.08488
Publikováno v:
Digital Investigation. 30:117-126
In this paper, we propose two methods to recover damaged audio files using deep neural networks. The presented audio file recovery methods differ from the conventional file carving-based recovery method because the former restore lost data, which are
Publikováno v:
Interspeech 2021.
The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field have direct
Autor:
Youngki Kwon, Bong-Jin Lee, Joon Son Chung, You Jin Kim, Yoohwan Kwon, Hee-Soo Heo, Soo-Whan Chung, Soyeon Choe
Publikováno v:
Interspeech 2021.
In this work, we present a novel audio-visual dataset for active speaker detection in the wild. A speaker is considered active when his or her face is visible and the voice is audible simultaneously. Although active speaker detection is a crucial pre
Publikováno v:
ICASSP
This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representations of a graph. The proposed
In this work, we propose an overlapped speech detection system trained as a three-class classifier. Unlike conventional systems that perform binary classification as to whether or not a frame contains overlapped speech, the proposed approach classifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95a8558010a57b68e17d6330a6b10626
http://arxiv.org/abs/2104.02878
http://arxiv.org/abs/2104.02878