Text-dependent speaker recognition using PLDA with uncertainty propagation

85 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.

End-to-end text-dependent speaker verification (2015, methodology): “Also, this baseline does not include other refining techniques such as ”uncertainty training” [10] that have been reported to give substantial additional gains under certain”
Spoofing and countermeasures for speaker verification: A survey (2015, methodology): “The underlying feature extraction, speaker modelling and classification approaches developed for text-independent systems, including i-vector and PLDA models, can also be applied within text-dependent systems with minor modifications (Larcher et al., 2013b; Stafylakis et al., 2013).”
End-to-End attention based text-dependent speaker verification (2016, methodology): “Better performance can be achieved by slightly modifying the older techniques such as GMM-UBM[4], GMM-SVM[9, 10] and i-vector/PLDA[11].”
Locally-connected and convolutional neural networks for small footprint speaker recognition (2015, unknown): “Utterance d-vectors were incrementally computed frame by frame, and improved latency by avoiding the computational costs associated with the latent variables of a factor analysis model [5], which occurred after utterance completion.”
Deep neural networks for small footprint text-dependent speaker verification (2014, methodology): “The i-vector-PLDA technique and its variants have also been successfully used in text-dependent speaker recognition tasks [8, 9, 10].”