May 20, 2017 · Specifically, a deep neural network (DNN) is trained to produce the posterior probabilities of different SNR levels or channel types given i- ...

Abstract—The mismatch between enrollment and test utter- ances due to different types of variabilities is a great challenge in speaker verification.

Specifically, a deep neural network DNN is trained to produce the posterior probabilities of different SNR levels or channel types given i-vectors as input.

Fingerprint. Dive into the research topics of 'DNN-Driven Mixture of PLDA for Robust Speaker Verification'. Together they form a unique fingerprint.

ABSTRACT. In speaker recognition, the mismatch between the enrollment and test utterances due to noise with different signal-to-noise.

This paper presents a development of previous research by P.Kenny, which deals with using a supervised PLDA mixture of two gender-dependent speaker verification ...

Specifically, a deep neural network (DNN) is trained to produce the posterior probabilities of different SNR levels or channel types given i-vectors as input.

Therefore, it solves many complicated pattern recognition problems and makes great progresses in correlation technique of Artificial Intelligence (AI).

The mismatch between enrollment and test utterances due to different types of variabilities is a great challenge in speaker verification.

SNR-independent mixture of PLDA (SI-mPLDA):. Deep Neural Network Driven Mixture of PLDA for Robust I-vector Speaker Verification. References: •M. W. Mak ...