Audio Feature Fusion is a feature-level fusion method that integrates acoustic features extracted from multiple audio signals or modalities into a unified representation to enhance discriminative power in multimodal or multipath audio analysis.
560
Publications
23.7K
Citations
1.8K
Authors
551
Institutions
Publications per year
2017–2026
299
Parents
Publications
560
Audio-Visual Emotion Recognition in Video Clips
Fatemeh Noroozi, Marina Marjanović, Angelina Njeguš et al. · IEEE Transactions on Affective Computing · 2017 · 266 citations · Full text
1–5 of 560
Authors
1.8K
- MP
7
h-index
- GPGerasimos Potamianos
IBM Research - Thomas J. Watson Research Center, United States
6 publications · 215 citations
6
h-index
- LN
6
h-index
- SP
6
h-index
- CN
6
h-index
1–5 of 1.8K
Institutions
551
Chinese Academy of Sciences
Beijing, China
12 h-index
35 publications
1.2K citations
Nanyang Technological University
Singapore, Singapore
10 h-index
26 publications
1.3K citations
Institute for Infocomm Research
Singapore, Singapore
10 h-index
34 publications
1.6K citations
University of Surrey
Guildford, United Kingdom
10 h-index
16 publications
634 citations
Northwestern Polytechnical University
Xi'an, China
10 h-index
22 publications
1.1K citations
University of Illinois Urbana-Champaign
Urbana, United States
9 h-index
19 publications
583 citations
Imperial College London
London, United Kingdom
8 h-index
22 publications
707 citations
University of Chinese Academy of Sciences
Beijing, China
7 h-index
17 publications
587 citations
1–8 of 551
Venues
- arXiv (Cornell University)
Repository · 23 publications · 685 citations
15
h-index
- IEEE Transactions on Multimedia
10 publications · 1.1K citations
10
h-index
- IEEE/ACM Transactions on Audio Speech and Language Processing
TASLP · 10 publications · 380 citations
10
h-index
- IEEE Access
8 publications · 457 citations
8
h-index
- Speech Communication
8 publications · 269 citations
8
h-index
1–5