306 citations
- University of Eastern FinlandFI61 papers
- University of HelsinkiFI16 papers
- Helsinki Institute of PhysicsFI7 papers
- Aalto UniversityFI5 papers
- Tampere UniversityFI4 papers
- EURECOMFR3 papers
- Institute for Infocomm ResearchSG3 papers
- National Institute of InformaticsJP3 papers
- Universidad Politécnica de MadridES3 papers
- University of JyväskyläFI3 papers
- Adolfo Ibáñez UniversityCL2 papers
- Bielefeld UniversityDE2 papers
Showing 2021 · cs.SDShow all
3 papers · 2 filters
cs.SD2021★ 4 cited
Optimizing Multi-Taper Features for Deep Speaker Verification
Xuechen Liu, Md Sahidullah, Tomi Kinnunen
Multi-taper estimators provide low-variance power spectrum estimates that can be used in place of the windowed discrete Fourier transform (DFT) to extract speech features such as m…
cs.SD2021
Parameterized Channel Normalization for Far-field Deep Speaker Verification
Xuechen Liu, Md Sahidullah, Tomi Kinnunen
We address far-field speaker verification with deep neural network (DNN) based speaker embedding extractor, where mismatch between enrollment and test data often comes from convolu…
cs.SD2021★ 3 cited
Learnable MFCCs for Speaker Verification
Xuechen Liu, Md Sahidullah, Tomi Kinnunen
We propose a learnable mel-frequency cepstral coefficient (MFCC) frontend architecture for deep neural network (DNN) based automatic speaker verification. Our architecture retains…