[HTML][HTML] A Comprehensive Review on Discriminant Analysis for Addressing Challenges of Class-Level Limitations, Small Sample Size, and Robustness
The classical linear discriminant analysis (LDA) algorithm has three primary drawbacks, ie,
small sample size problem, sensitivity to noise and outliers, and inability to deal with multi …
small sample size problem, sensitivity to noise and outliers, and inability to deal with multi …
[書籍][B] Machine learning for speaker recognition
This book will help readers understand fundamental and advanced statistical models and
deep learning models for robust speaker recognition and domain adaptation. This useful …
deep learning models for robust speaker recognition and domain adaptation. This useful …
Mixture of PLDA for noise robust i-vector speaker verification
In real-world environments, noisy utterances with variable noise levels are recorded and
then converted to i-vectors for cosine distance or PLDA scoring. This paper investigates the …
then converted to i-vectors for cosine distance or PLDA scoring. This paper investigates the …
Cancellable speech template via random binary orthogonal matrices projection hashing
The increasing advancement of mobile technology explosively popularizes the mobile
devices (eg iPhone, iPad). A large number of mobile devices provide great convenience and …
devices (eg iPhone, iPad). A large number of mobile devices provide great convenience and …
Spatial map** Zataria multiflora using different machine-learning algorithms
Understanding the relationships between environmental factors that influence the
distribution of medicinal plants is crucial to identifying suitable habitats for them. Studies …
distribution of medicinal plants is crucial to identifying suitable habitats for them. Studies …
DNN-driven mixture of PLDA for robust speaker verification
The mismatch between enrollment and test utterances due to different types of variabilities is
a great challenge in speaker verification. Based on the observation that the SNR-level …
a great challenge in speaker verification. Based on the observation that the SNR-level …
[PDF][PDF] Analysis of Methods and Techniques Used for Speaker Identification, Recognition, and Verification: A Study on Quarter-Century Research Outcomes
The theories and applications of speaker identification, recognition, and verification are
among the well-established fields. Many publications and advances in the relevant products …
among the well-established fields. Many publications and advances in the relevant products …
[PDF][PDF] From adaptive score normalization to adaptive data normalization for speaker verification systems
Abstract Domain and trial-dependent mismatch between training and evaluation data can
severely affect the performance of speaker verification systems, and are usually addressed …
severely affect the performance of speaker verification systems, and are usually addressed …
Use of Neumann series decomposition to fit the Weighted Euclidean distance and Inner product scoring models in automatic speaker recognition
M Djellab, N Mehallegue, A Achi - Pattern Recognition Letters, 2019 - Elsevier
It is commonly agreed that the main performance indicators in real life biometric applications
are: accuracy, calibration quality and computation cost in the case of large databases use …
are: accuracy, calibration quality and computation cost in the case of large databases use …
SNR-invariant PLDA with multiple speaker subspaces
N Li, MW Mak - … Conference on Acoustics, Speech and Signal …, 2016 - ieeexplore.ieee.org
To deal with the mismatch between the enrollment and test utterances caused by noise with
different signal-to-noise ratios (SNR), we have recently proposed an SNR-invariant PLDA …
different signal-to-noise ratios (SNR), we have recently proposed an SNR-invariant PLDA …