The CORAL+ algorithm for unsupervised domain adaptation of PLDA

KA Lee, Q Wang, T Koshinaka - ICASSP 2019-2019 IEEE …, 2019 - ieeexplore.ieee.org
State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker
embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) …

Multi-level deep neural network adaptation for speaker verification using MMD and consistency regularization

W Lin, MM Mak, N Li, D Su, D Yu - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
Adapting speaker verification (SV) systems to a new environment is a very challenging task.
Current adaptation methods in SV mainly focus on the backend, ie, adaptation is carried out …

Multisource i-vectors domain adaptation using maximum mean discrepancy based autoencoders

W Lin, MW Mak, JT Chien - IEEE/ACM Transactions on Audio …, 2018 - ieeexplore.ieee.org
Like many machine learning tasks, the performance of speaker verification (SV) systems
degrades when training and test data come from very different distributions. What's more …

An investigation of domain adaptation in speaker embedding space for speaker recognition

F Bahmaninezhad, C Zhang, JHL Hansen - Speech Communication, 2021 - Elsevier
Speaker recognition continues to grow as a research challenge in the field with expanded
application in commercial, forensic, educational and general speech technology interfaces …

Assessing child communication engagement and statistical speech patterns for American English via speech recognition in naturalistic active learning spaces

R Lileikyte, D Irvin, JHL Hansen - Speech Communication, 2022 - Elsevier
Assessing child growth in terms of speech and language development is a critical indicator
of long term learning ability and life-long development progress. The earlier a child who is at …

UTD-CRSS systems for 2018 NIST speaker recognition evaluation

C Zhang, F Bahmaninezhad, S Ranjan… - ICASSP 2019-2019 …, 2019 - ieeexplore.ieee.org
In this study, we present systems submitted by the Center for Robust Speech Systems
(CRSS) from UTDallas to NIST SRE 2018 (SRE18). Three alternative front-end speaker …

A framework for adapting DNN speaker embedding across languages

W Lin, MW Mak, N Li, D Su, D Yu - IEEE/ACM Transactions on …, 2020 - ieeexplore.ieee.org
Language mismatch remains a major hindrance to the extensive deployment of speaker
verification (SV) systems. Current language adaptation methods in SV mainly rely on linear …

A generalized framework for domain adaptation of plda in speaker recognition

Q Wang, K Okabe, KA Lee… - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
This paper proposes a generalized framework for domain adaptation of Probabilistic Linear
Discriminant Analysis (PLDA) in speaker recognition. It not only includes several existing …

Generative x-vectors for text-independent speaker verification

L Xu, RK Das, E Yılmaz, J Yang… - 2018 IEEE Spoken …, 2018 - ieeexplore.ieee.org
Speaker verification (SV) systems using deep neural network embeddings, so-called the x-
vector systems, are becoming popular due to its good performance superior to the i-vector …

I4U submission to NIST SRE 2018: Leveraging from a decade of shared experiences

KA Lee, V Hautamaki, T Kinnunen… - arxiv preprint arxiv …, 2019 - arxiv.org
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition
evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the …