Amanote Research
Register
Sign In
End-To-End DNN Based Speaker Recognition Inspired by I-Vector and PLDA
doi 10.1109/icassp.2018.8461958
Full Text
Open PDF
Abstract
Available in
full text
Date
April 1, 2018
Authors
Johan Rohdin
Anna Silnova
Mireia Diez
Oldrch Plchot
Pavel Matejka
Lukas Burget
Publisher
IEEE
Related search
Domain-Invariant I-Vector Feature Extraction for PLDA Speaker Verification
Nexus DNN for Speech and Speaker Recognition
International Journal of Engineering and Advanced Technology
Engineering
Computer Science Applications
Environmental Engineering
Adversarial Regularization for End-To-End Robust Speaker Verification
Channel Variability Synthesis in I-Vector Speaker Recognition
Channel Compensation for Speaker Recognition Using MAP Adapted PLDA and Denoising DNNs
End-To-End Speaker Identification in Noisy and Reverberant Environments Using Raw Waveform Convolutional Neural Networks
End-To-End Speech Recognition With Auditory Attention for Multi-Microphone Distance Speech Recognition
Gist+RatSLAM: An Incremental Bio-Inspired Place Recognition Front-End for RatSLAM
Unidirectional Neural Network Architectures for End-To-End Automatic Speech Recognition