Robust Speech Recognition is a speech recognition methodology designed to maintain high accuracy and reliability in the presence of acoustic variations, environmental noise, speaker diversity, and other adverse conditions that typically degrade performance in conventional systems.
1.9K
Publications
100.2K
Citations
3.1K
Authors
734
Institutions
Publications per year
2017–2026
290
Parents
Publications
1.9K
X-Vectors: Robust DNN Embeddings for Speaker Recognition
David Snyder, Daniel Garcia-Romero, Gregory Sell et al. · 2018 · 2.7K citations
Hynek Heřmanský, N. Morgan · IEEE Transactions on Speech and Audio Processing · 1994 · 1.8K citations
1–5 of 1.9K
Authors
3.1K
- JH
32
h-index
- RM
28
h-index
- AA
25
h-index
- MG
23
h-index
- DW
21
h-index
1–5 of 3.1K
Institutions
734
Carnegie Mellon University
Pittsburgh, United States
34 h-index
147 publications
8.4K citations
Microsoft (United States)
Redmond, United States
28 h-index
117 publications
11.3K citations
University of Cambridge
Cambridge, United Kingdom
25 h-index
77 publications
4.5K citations
The Ohio State University
Columbus, United States
25 h-index
72 publications
7.3K citations
AT&T (United States)
Bedminster, United States
25 h-index
71 publications
7.1K citations
SRI International
Menlo Park, United States
25 h-index
102 publications
5.6K citations
NTT (Japan)
Tokyo, Japan
23 h-index
103 publications
5.9K citations
The University of Texas at Dallas
Richardson, United States
20 h-index
78 publications
3.2K citations
1–8 of 734
Venues
- IEEE Transactions on Speech and Audio Processing
70 publications · 11.5K citations
42
h-index
- Speech Communication
75 publications · 6.5K citations
40
h-index
- IEEE Transactions on Audio Speech and Language Processing
78 publications · 3.4K citations
33
h-index
- IEEE/ACM Transactions on Audio Speech and Language Processing
TASLP · 38 publications · 3K citations
25
h-index
- Computer Speech & Language
34 publications · 1.8K citations
22
h-index
1–5