A Discriminative Condition-Aware Backend for Speaker Verification

Ferrer, Luciana; McLaren, Mitchell

doi:10.1109/icassp40776.2020.9053485

Cited by 11 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, there are three kinds of representative methods to improve the backend. The first category is about PLDA, such as Neural PLDA [17], discriminative PLDA (DPLDA) [18], heavy-tailed PLDA (HT-PLDA) [19], multi-objective optimization training of PLDA (Mot-PLDA) [20] and etc. The second is to add an additional trainable neural network module, e.g., decision residual networks (Dr-vectors) [21], deep learning backend (DLB) [22] and tied variational autoencoder (TVAE) [23].…”

Section: Introductionmentioning

confidence: 99%

Crossed-Time Delay Neural Network for Speaker Recognition

Chen

Liang

Shi

et al. 2021

MultiMedia Modeling

View full text Add to dashboard Cite

Time Delay Neural Network (TDNN) is a well-performing structure for DNN-based speaker recognition systems. In this paper we introduce a novel structure Crossed-Time Delay Neural Network (CTDNN) to enhance the performance of current TDNN. Inspired by the multi-filters setting of convolution layer from convolution neural network, we set multiple time delay units each with different context size at the bottom layer and construct a multilayer parallel network. The proposed CTDNN gives significant improvements over original TDNN on both speaker verification and identification tasks. It outperforms in VoxCeleb1 dataset in verification experiment with a 2.6% absolute Equal Error Rate improvement. In few shots condition CTDNN reaches 90.4% identification accuracy, which doubles the identification accuracy of original TDNN. We also compare the proposed CTDNN with another new variant of TDNN, FTDNN, which shows that our model has a 36% absolute identification accuracy improvement under few shots condition and can better handle training of a larger batch in a shorter training time, which better utilize the calculation resources.

show abstract

Section: Introductionmentioning

confidence: 99%

Crossed-Time Delay Neural Network for Speaker Recognition

Chen

Liang

Shi

et al. 2021

MultiMedia Modeling

View full text Add to dashboard Cite

show abstract

“…We proposed to capture the information about the conditions that affect calibration in a sideinformation vector, which was then used to determine the parameters of the calibration stage. In our first paper (Ferrer and McLaren, 2020a), the sideinformation vector was generated by a separate model, which was trained to predict labeled conditions in the training data. These condition labels were derived from the available metadata in each of the training datasets, which had different levels of detail depending on the dataset.…”

Section: Condition-aware Discriminative Backendmentioning

confidence: 99%

A Speaker Verification Backend for Improved Calibration Performance across Varying Conditions

Ferrer¹,

McLaren²

2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

Self Cite

View full text Add to dashboard Cite

In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting speaker embeddings with a deep neural network and processing them through a backend composed of probabilistic linear discriminant analysis (PLDA) and global logistic regression score calibration. This method is known to result in systems that work poorly on conditions different from those used to train the calibration model. We propose to modify the standard backend, introducing an adaptive calibrator that uses duration and other automatically extracted side-information to adapt to the conditions of the inputs. The backend is trained discriminatively to optimize binary cross-entropy. When trained on a number of diverse datasets that are labeled only with respect to speaker, the proposed backend consistently and, in some cases, dramatically improves calibration, compared to the standard PLDA approach, on a number of held-out datasets, some of which are markedly different from the training data. Discrimination performance is also consistently improved. We show that joint training of the PLDA and the adaptive calibrator is essential-the same benefits cannot be achieved when freezing PLDA and fine-tuning the calibrator. To our knowledge, the results in this paper are the first evidence in the literature that it is possible to develop a speaker verification system with robust out-of-the-box performance on a large variety of conditions.

show abstract

“…Such scores instability impairs SR systems in real applications. In order to deal with this problem different calibration strategies [8], [9] and compensation techniques [10], [11] were implemented.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems

Lavrentyeva¹,

Novoselov²,

Shulipa³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep speaker embedding extractors have already become new state-of-the-art systems in the speaker verification field. However, the problem of verification score calibration for such systems often remains out of focus. An irrelevant score calibration leads to serious issues, especially in the case of unknown acoustic conditions, even if we use a strong speaker verification system in terms of threshold-free metrics.This paper presents an investigation over several methods of score calibration: a classical approach based on the logistic regression model; the recently presented magnitude estimation network MagnetO that uses activations from the pooling layer of the trained deep speaker extractor and generalization of such approach based on separate scale and offset prediction neural networks.An additional focus of this research is to estimate the impact of score normalization on the calibration performance of the system.The obtained results demonstrate that there are no serious problems if in-domain development data are used for calibration tuning. Otherwise, a trade-off between good calibration performance and threshold-free system quality arises. In most cases using adaptive s-norm helps to stabilize score distributions and to improve system performance.Meanwhile, some experiments demonstrate that novel approaches have their limits in score stabilization on several datasets.

show abstract

A Discriminative Condition-Aware Backend for Speaker Verification

Cited by 11 publications

References 18 publications

Crossed-Time Delay Neural Network for Speaker Recognition

Crossed-Time Delay Neural Network for Speaker Recognition

A Speaker Verification Backend for Improved Calibration Performance across Varying Conditions

Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems

Contact Info

Product

Resources

About