142 citations
- Duke UniversityUS18 papers
- Ludwig-Maximilians-Universität MünchenDE9 papers
- Sun Yat-sen UniversityCN8 papers
- Peking UniversityCN7 papers
- Xi’an Jiaotong-Liverpool UniversityCN7 papers
- Institute of Science and Technology AustriaAT5 papers
- Wuhan UniversityCN5 papers
- Zhejiang UniversityCN5 papers
- Beijing Normal UniversityCN4 papers
- Illinois Institute of TechnologyUS4 papers
- Pohang University of Science and TechnologyKR4 papers
- Triangle Universities Nuclear LaboratoryUS4 papers
8 papers · 1 filter
A mean field limit for the Hamiltonian Vlasov system
Robert A. Neiss, Peter Pickl
The derivation of effective equations for interacting many body systems has seen a lot of progress in the recent years. While dealing with classical systems, singular potentials ar…
End-to-end Language Identification using NetFV and NetVLAD
Jinkun Chen, Weicheng Cai, Danwei Cai +3
In this paper, we apply the NetFV and NetVLAD layers for the end-to-end language identification task. NetFV and NetVLAD layers are the differentiable implementations of the standar…
Mean-field limits of particles in interaction with quantized radiation fields
Nikolai Leopold, Peter Pickl
We report on a simple strategy to treat mean-field limits of quantum mechanical systems in which a large number of particles weakly couple to a second-quantized radiation field. Ex…
Analysis of Length Normalization in End-to-End Speaker Verification System
Weicheng Cai, Jinkun Chen, Ming Li
The classical i-vectors and the latest end-to-end deep speaker embeddings are the two representative categories of utterance-level representations in automatic speaker verification…
Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System
Weicheng Cai, Jinkun Chen, Ming Li
In this paper, we explore the encoding/pooling layer and loss function in the end-to-end speaker and language recognition system. First, a unified and interpretable end-to-end syst…
A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification
Weicheng Cai, Zexin Cai, Xiang Zhang +2
A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoreti…