Deep bottleneck features for i-vector based text-independent speaker verification

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

VoxCeleb2: Deep Speaker Recognition (2018, background): “The success of deep learning in computer vision and speech recognition has motivated the use of deep neural networks (DNN) as feature extractors combined with classifiers, though not trained end-to-end [15, 16, 17, 18, 19].”
Deep Speaker: an End-to-End Neural Speaker Embedding System (2017, background): “One approach is to train a GMM on bottleneck features extracted from a DNN, and then extract i-vectors [22].”
Speaker recognition based on deep learning: An overview (2020, background): “[46] proposed to take speaker identity as the training target, under the conjecture that this training target should be able to improve the robustness of the phonetic variability of BNF.”
Deep neural network-based speaker embeddings for end-to-end speaker verification (2016, methodology): “Prior work includes framelevel models that compute probabilities over a fixed list of speakers [15, 16, 17, 18, 19].”