Browsing by Author "Mak, Man-Wai"

Now showing 1 - 9 of 9

DEEP NEURAL NETWORK DRIVEN MIXTURE OF PLDA FOR ROBUST I-VECTOR SPEAKER VERIFICATION
(2016-01-01)
Li, Na
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
In speaker recognition, the mismatch between the enrollment and test utterances due to noise with different signal-to-noise ratios (SNRs) is a great challenge. Based on the observation that noise-level variability causes the i-vectors to form heterogeneous clusters, this paper proposes using an SNR-aware deep neural network (DNN) to guide the training of PLDA mixture models. Specifically, given an i-vector, the SNR posterior probabilities produced by the DNN are used as the posteriors of indicator variables of the mixture model. As a result, the proposed model provides a more reasonable soft division of the i-vector space compared to the conventional mixture of PLDA. During verification, given a test trial, the marginal likelihoods from individual PLDA models are linearly combined by the posterior probabilities of SNR levels computed by the DNN. Experimental results for SNR mismatch tasks based on NIST 2012 SRE suggest that the proposed model is more effective than PLDA and conventional mixture of PLDA for handling heterogeneous corpora.
Discriminative subspace modeling of SNR and duration variabilities for robust speaker verification
(2017-09-01)
Li, Na
;
Mak, Man-Wai
;
Lin, Wei-Wei
;
Chien, Jen-Tzung
;
電機工程學系
Although i-vectors together with probabilistic LDA (PLDA) have achieved a great success in speaker verification, how to suppress the undesirable effects caused by the variability in utterance length and background noise level is still a challenge. This paper aims to improve the robustness of i-vector based speaker verification systems by compensating for the utterance-length variability and noise-level variability. Inspired by the recent findings that noise-level variability can be modeled by a signal-to-noise ratio (SNR) subspace and that duration variability can be modeled as additive noise in the i-vector space, we propose to add an SNR factor and a duration factor to the PLDA model. In this framework, we assume that i-vectors derived from utterances with comparable durations share similar duration-specific information and that i-vectors extracted from utterances within. a narrow SNR range have similar SNR-specific information. Based on these assumptions, an i-vector can be represented as a linear combination of four components: speaker, SNR, duration, and channel. A variational Bayes algorithm is developed to infer this latent variable model via a discriminative subspace training procedure. In the testing stage, different variabilities are compensated for when computing the likelihood ratio. Experiments on Common Conditions 1 and 4 in MST 2012 SRE show that the proposed model outperforms the conventional PLDA and SNR-invariant PLDA. Results also show that the proposed model performs better than the uncertainty-propagation PLDA (UP-PLDA) for long test utterances. (C) 2017 Elsevier Ltd. All rights reserved.
DNN-Driven Mixture of PLDA for Robust Speaker Verification
(2017-06-01)
Li, Na
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
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 variability or channel-type variability causes heterogeneous clusters in i-vector space, this paper proposes to apply supervised learning to drive or guide the learning of probabilistic linear discriminant analysis (PLDA) mixture models. Specifically, a deep neural network (DNN) is trained to produce the posterior probabilities of different SNR levels or channel types given i-vectors as input. These posteriors then replace the posterior probabilities of indicator variables in the mixture of PLDA. The discriminative training causes the mixture model to perform more reasonable soft divisions of the i-vector space as compared to the conventional mixture of PLDA. During verification, given a test i-vector and a target-speaker's i-vector, the marginal likelihood for the same-speaker hypothesis is obtained by summing the component likelihoods weighted by the component posteriors produced by the DNN, and likewise for the different-speaker hypothesis. Results based on NIST 2012 SRE demonstrate that the proposed scheme leads to better performance under more realistic situations where both training and test utterances cover a wide range of SNRs and different channel types. Unlike the previous SNR-dependent mixture of PLDA which only focuses on SNR mismatch, the proposed model is more general and is potentially applicable to addressing different types of variability in speech.
Fast scoring for PLDA with uncertainty propagation via i-vector grouping
(2017-09-01)
Lin, Wei-wei
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
The i-vector/PLDA framework has gained huge popularity in text-independent speaker verification. This approach, however, lacks the ability to represent the reliability of i-vectors. As a result, the framework performs poorly when presented with utterances of arbitrary duration. To address this problem, a method called uncertainty propagation (UP) was proposed to explicitly model the reliability of an i-vector by an utterance-dependent loading matrix. However, the utterance-dependent matrix greatly complicates the evaluation of likelihood scores. As a result, PLDA with UP, or PLDA-UP in short, is far more computational intensive than the conventional PLDA. In this paper, we propose to group i-vectors with similar reliability, and for each group the utterance-dependent loading matrices are replaced by a representative one. This arrangement allows us to pre-compute a set of representative matrices that cover all possible i-vectors, thereby greatly reducing the computational cost of PLDA-UP while preserving its ability in discriminating the reliability of i-vectors. Experiments on NIST 2012 SRE show that the proposed method can perform as good as the PLDA with UP while the scoring time is only 3.18% of it. (C) 2017 Elsevier Ltd. All rights reserved.
Guest Editorial: Modern Speech Processing and Learning
(1970-01-01)
Chien, Jen-Tzung
;
Mak, Man-Wai
;
電機工程學系
;
Department of Electrical and Computer Engineering
Guest Editorial: Modern Speech Processing and Learning
(2020-08-01)
Chien, Jen-Tzung
;
Mak, Man-Wai
;
電機工程學系
;
Department of Electrical and Computer Engineering
Multisource I-Vectors Domain Adaptation Using Maximum Mean Discrepancy Based Autoencoders
(2018-12-01)
Lin, Wei-wei
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
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, both training and test data themselves could be composed of heterogeneous subsets. These multisource mismatches are detrimental to SV performance. This paper proposes incorporating maximum mean discrepancy (MMD) into the loss function of autoencoders to reduce these mismatches. MMD is a non-parametric method for measuring the distance between two probability distributions. With a properly chosen kernel, MMD can match up to infinite moments of data distributions. We generalize MMD to measure the discrepancies of multiple distributions. We call the generalized MMD domainwise MMD. Using domainwise MMD as an objective function, we propose two autoencoders, namely nuisance-attribute autoencoder (NAE) and domain-invariant autoencoder (DAE), for multisource i-vector adaptation. NAE encodes the features that cause most of the multisource mismatch measured by domainwise MMD. DAE directly encodes the features that minimize the multisource mismatch. Using these MMD-based autoencoders as a preprocessing step for PLDA training, we achieve a relative improvement of 19.2% EER on the NIST 2016 SRE compared to PLDA without adaptation. We also found that MMD-based autoencoders are more robust to unseen domains. In the domain robustness experiments, MMD-based autoencoders show 6.8% and 5.2% improvements over IDVC on female and male Cantonese speakers, respectively.
SEMI-SUPERVISED NUISANCE-ATTRIBUTE NETWORKS FOR DOMAIN ADAPTATION
(2019-01-01)
Lin, Weiwei
;
Mak, Man-Wai
;
Tu, Youzhi
;
Chien, Jen-Tzung
;
電機工程學系
How to overcome the training and test data mismatch in speaker verification systems has been a focus of research recently. In this paper, we propose a semi-supervised nuisance attribute network ( SNAN) to reduce the domain mismatch in i-vectors and x-vectors. SNANs are based on the idea of nuisance attribute removal in inter-dataset variability compensation ( IDVC). But instead of measuring the domain variability through the dataset means, SNANs use the maximum mean discrepancy ( MMD) as part of their loss function, which enables the network to find nuisance directions in which domain variability is measured up to infinite moment. The architecture of SNANs also allows us to incorporate the out-of-domain speaker labels into the semi-supervised training process through the center loss and triplet loss. Using SNANs as a preprocessing step for PLDA training, we achieve a relative improvement of 11.8% in EER on NIST 2016 SRE compared to PLDA without adaptation. We also found that the semi-supervised approach can further improve SNANs' performance.
Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification
(2020-01-01)
Tu, Youzhi
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
Domain mismatch is a common problem in speaker verification (SV) and often causes performance degradation. For the system relying on the Gaussian PLDA backend to suppress the channel variability, the performance would be further limited if there is no Gaussianity constraint on the learned embeddings. This paper proposes an information-maximized variational domain adversarial neural network (InfoVDANN) that incorporates an InfoVAE into domain adversarial training (DAT) to reduce domain mismatch and simultaneously meet the Gaussianity requirement of the PLDA backend. Specifically, DAT is applied to produce speaker discriminative and domain-invariant features, while the InfoVAE performs variational regularization on the embedded features so that they follow a Gaussian distribution. Another benefit of the InfoVAE is that it avoids posterior collapse in VAEs by preserving the mutual information between the embedded features and the training set so that extra speaker information can be retained in the features. Experiments on both SRE16 and SRE18-CMN2 show that the InfoVDANN outperforms the recent VDANN, which suggests that increasing the mutual information between the embedded features and input features enables the InfoVDANN to extract extra speaker information that is otherwise not possible.