paper-with-me

Papers

Local Training for PLDA in Speaker Verification

2016-09-27 · Chenghui Zhao, Lantian Li, Dong Wang, April Pu

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly expensive in most cases. A possible approach to mitigate the problem is various unsupervised adaptation methods, which use unlabeled data to adapt the PLDA scattering matrices to the target domain. In this paper, we present a new local training' approach that utilizes inaccurate but much cheaper local labels to train the PLDA model. These local labels discriminate speakers within a single conversion only, and so are much easier to obtain compared to the normal global labels'. Our experiments show that the proposed approach can deliver significant performance improvement, particularly with limited globally-labeled data.

📄 PDF Abstract BibTeX arXiv:1609.08433

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker Verification

Similar Papers 제목 키워드 기반

NPLDA: A Deep Neural PLDA Model for Speaker Verification

2020-02-10 · Shreyas Ramoji, Prashant Krishnan, Sriram Ganapathy

The state-of-art approach for speaker verification consists of a neural network based embedding extractor along with a backend generative model such as the Probabilistic Linear Discriminant Analysis (PLDA). In this work,…

Speaker RecognitionSpeaker Verification

Neural PLDA Modeling for End-to-End Speaker Verification

2020-08-11 · Shreyas Ramoji, Prashant Krishnan, Sriram Ganapathy

While deep learning models have made significant advances in supervised classification problems, the application of these models for out-of-set verification tasks like speaker recognition has been limited to deriving fea…

Speaker RecognitionSpeaker Verification

Text-Independent Speaker Verification Based on Deep Neural Networks and Segmental Dynamic Time Warping

2018-06-26 · Mohamed Adel, Mohamed Afify, Akram Gaballah

In this paper we present a new method for text-independent speaker verification that combines segmental dynamic time warping (SDTW) and the d-vector approach. The d-vectors, generated from a feed forward deep neural netw…

Dynamic Time WarpingSpeaker VerificationText-Independent Speaker Verification

Multiobjective Optimization Training of PLDA for Speaker Verification

2018-08-25 · Liang He, Xianhong Chen, Can Xu, Jia Liu

Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PLDA are often estimated by maximizing th…

Multiobjective OptimizationSpeaker VerificationText-Independent Speaker Verification

Joint Speaker Encoder and Neural Back-end Model for Fully End-to-End Automatic Speaker Verification with Multiple Enrollment Utterances

2022-09-01 · Chang Zeng, Xiaoxiao Miao, Xin Wang, Erica Cooper 외

Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-base…

Data AugmentationSpeaker Verification