Speech segregation is the perceptual process by which a listener isolates and organizes target speech signals from concurrent acoustic sources in a complex auditory environment, differing from general auditory scene analysis by focusing specifically on the extraction of linguistically meaningful vocal streams.
537
Publications
39.9K
Citations
1.1K
Authors
406
Institutions
Publications per year
2017–2026
202
Publications
537
Deep clustering: Discriminative embeddings for segmentation and separation
John R. Hershey, Zhuo Chen, Jonathan Le Roux et al. · 2016 · 1.4K citations
1–5 of 537
Authors
1.1K
- DW
34
h-index
- JR
18
h-index
- DY
13
h-index
- JL
12
h-index
- TN
12
h-index
1–5 of 1.1K
Institutions
406
The Ohio State University
Columbus, United States
37 h-index
146 publications
17.2K citations
Columbia University
New York, United States
17 h-index
39 publications
10.2K citations
Google (United States)
Mountain View, United States
15 h-index
60 publications
10K citations
NTT (Japan)
Tokyo, Japan
14 h-index
56 publications
2.8K citations
Mitsubishi Electric (United States)
Cypress, United States
14 h-index
39 publications
7.8K citations
University of Science and Technology of China
Hefei, China
12 h-index
36 publications
1.5K citations
University of Toronto
Toronto, Canada
12 h-index
20 publications
882 citations
University of Sheffield
Sheffield, United Kingdom
12 h-index
22 publications
2.5K citations
1–8 of 406
Venues
- The Journal of the Acoustical Society of America
JASA · 54 publications · 3.4K citations
31
h-index
- IEEE/ACM Transactions on Audio Speech and Language Processing
TASLP · 36 publications · 7.2K citations
25
h-index
- IEEE Transactions on Audio Speech and Language Processing
21 publications · 2.6K citations
19
h-index
- arXiv (Cornell University)
Repository · 24 publications · 764 citations
15
h-index
- Speech Communication
16 publications · 469 citations
13
h-index
1–5