arXiv subjects

Helen Meng

Publications and source records attributed to Helen Meng.

226 records · Page 13Linked to original sources

arXiv2020

Multi-Target Emotional Voice Conversion With Neural Vocoders

Emotional voice conversion (EVC) is one way to generate expressive synthetic speech. Previous approaches mainly focused on modeling one-to-one mapping, i.e., conversion from one emotional state to another emotional state, with Mel-cepstral vocoders. In this paper, we investigate building a multi-target EVC (MTEVC) architecture, which combines a deep bidirectional long-short term memory (DBLSTM)-based conversion model and a neural vocoder. Phonetic posteriorgrams (PPGs) containing rich linguistic information are incorporated into the conversion model as auxiliary input features, which boost the conversion performance. To leverage the advantages of the newly emerged neural vocoders, we investigate the conditional WaveNet and flow-based WaveNet (FloWaveNet) as speech generators. The vocoders take in additional speaker information and emotion information as auxiliary features and are trained with a multi-speaker and multi-emotion speech corpus. Objective metrics and subjective evaluation of the experimental results verify the efficacy of the proposed MTEVC architecture for EVC.

eess.AS↗

arXiv2020

Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

Speaker verification systems usually suffer from the mismatch problem between training and evaluation data, such as speaker population mismatch, the channel and environment variations. In order to address this issue, it requires the system to have good generalization ability on unseen data. In this work, we incorporate Bayesian neural networks (BNNs) into the deep neural network (DNN) x-vector speaker verification system to improve the system's generalization ability. With the weight uncertainty modeling provided by BNNs, we expect the system could generalize better on the evaluation data and make verification decisions more accurately. Our experiment results indicate that the DNN x-vector system could benefit from BNNs especially when the mismatch problem is severe for evaluations using out-of-domain data. Specifically, results show that the system could benefit from BNNs by a relative EER decrease of 2.66% and 2.32% respectively for short- and long-utterance in-domain evaluations. Additionally, the fusion of DNN x-vector and Bayesian x-vector systems could achieve further improvement. Moreover, experiments conducted by out-of-domain evaluations, e.g. models trained on Voxceleb1 while evaluated on NIST SRE10 core test, suggest that BNNs could bring a larger relative EER decrease of around 4.69%.

eess.AS↗

arXiv2020

Defense against adversarial attacks on spoofing countermeasures of ASV

Various forefront countermeasure methods for automatic speaker verification (ASV) with considerable performance in anti-spoofing are proposed in the ASVspoof 2019 challenge. However, previous work has shown that countermeasure models are vulnerable to adversarial examples indistinguishable from natural data. A good countermeasure model should not only be robust against spoofing audio, including synthetic, converted, and replayed audios; but counteract deliberately generated examples by malicious adversaries. In this work, we introduce a passive defense method, spatial smoothing, and a proactive defense method, adversarial training, to mitigate the vulnerability of ASV spoofing countermeasure models against adversarial examples. This paper is among the first to use defense methods to improve the robustness of ASV spoofing countermeasure models under adversarial attacks. The experimental results show that these two defense methods positively help spoofing countermeasure models counter adversarial examples.

eess.AS↗

arXiv2020

Adversarial Attacks on GMM i-vector based Speaker Verification Systems

This work investigates the vulnerability of Gaussian Mixture Model (GMM) i-vector based speaker verification systems to adversarial attacks, and the transferability of adversarial samples crafted from GMM i-vector based systems to x-vector based systems. In detail, we formulate the GMM i-vector system as a scoring function of enrollment and testing utterance pairs. Then we leverage the fast gradient sign method (FGSM) to optimize testing utterances for adversarial samples generation. These adversarial samples are used to attack both GMM i-vector and x-vector systems. We measure the system vulnerability by the degradation of equal error rate and false acceptance rate. Experiment results show that GMM i-vector systems are seriously vulnerable to adversarial attacks, and the crafted adversarial samples prove to be transferable and pose threats to neuralnetwork speaker embedding based systems (e.g. x-vector systems).

eess.AS↗

arXiv2020

Deep segmental phonetic posterior-grams based discovery of non-categories in L2 English speech

Second language (L2) speech is often labeled with the native, phone categories. However, in many cases, it is difficult to decide on a categorical phone that an L2 segment belongs to. These segments are regarded as non-categories. Most existing approaches for Mispronunciation Detection and Diagnosis (MDD) are only concerned with categorical errors, i.e. a phone category is inserted, deleted or substituted by another. However, non-categorical errors are not considered. To model these non-categorical errors, this work aims at exploring non-categorical patterns to extend the categorical phone set. We apply a phonetic segment classifier to generate segmental phonetic posterior-grams (SPPGs) to represent phone segment-level information. And then we explore the non-categories by looking for the SPPGs with more than one peak. Compared with the baseline system, this approach explores more non-categorical patterns, and also perceptual experimental results show that the explored non-categories are more accurate with increased confusion degree by 7.3% and 7.5% under two different measures. Finally, we preliminarily analyze the reason behind those non-categories.

cs.CL↗

arXiv2020

Audio-visual Recognition of Overlapped speech for the LRS2 dataset

Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech recognition. Three issues associated with the construction of audio-visual speech recognition (AVSR) systems are addressed. First, the basic architecture designs i.e. end-to-end and hybrid of AVSR systems are investigated. Second, purposefully designed modality fusion gates are used to robustly integrate the audio and visual features. Third, in contrast to a traditional pipelined architecture containing explicit speech separation and recognition components, a streamlined and integrated AVSR system optimized consistently using the lattice-free MMI (LF-MMI) discriminative criterion is also proposed. The proposed LF-MMI time-delay neural network (TDNN) system establishes the state-of-the-art for the LRS2 dataset. Experiments on overlapped speech simulated from the LRS2 dataset suggest the proposed AVSR system outperformed the audio only baseline LF-MMI DNN system by up to 29.98\% absolute in word error rate (WER) reduction, and produced recognition performance comparable to a more complex pipelined system. Consistent performance improvements of 4.89\% absolute in WER reduction over the baseline AVSR system using feature fusion are also obtained.

eess.AS↗

arXiv2019

Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification

High-performance spoofing countermeasure systems for automatic speaker verification (ASV) have been proposed in the ASVspoof 2019 challenge. However, the robustness of such systems under adversarial attacks has not been studied yet. In this paper, we investigate the vulnerability of spoofing countermeasures for ASV under both white-box and black-box adversarial attacks with the fast gradient sign method (FGSM) and the projected gradient descent (PGD) method. We implement high-performing countermeasure models in the ASVspoof 2019 challenge and conduct adversarial attacks on them. We compare performance of black-box attacks across spoofing countermeasure models with different network architectures and different amount of model parameters. The experimental results show that all implemented countermeasure models are vulnerable to FGSM and PGD attacks under the scenario of white-box attack. The more dangerous black-box attacks also prove to be effective by the experimental results.

eess.AS↗

arXiv2019

Semi-Supervised Graph Classification: A Hierarchical Graph Perspective

Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a protein in a protein-protein interaction network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. For example, in a social network, a group of people with shared interests forms a user group, whereas a number of user groups are interconnected via interactions or common members. We study the node classification problem in the hierarchical graph where a `node' is a graph instance, e.g., a user group in the above example. As labels are usually limited in real-world data, we design two novel semi-supervised solutions named \underline{SE}mi-supervised gr\underline{A}ph c\underline{L}assification via \underline{C}autious/\underline{A}ctive \underline{I}teration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative framework that takes turns to build or update two classifiers, one working at the graph instance level and the other at the hierarchical graph level. To simplify the representation of the hierarchical graph, we propose a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors. Through experiments on synthetic data and Tencent QQ group data, we demonstrate that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations.

cs.CV↗

arXiv2016

Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition

Feature subspace selection is an important part in speech emotion recognition. Most of the studies are devoted to finding a feature subspace for representing all emotions. However, some studies have indicated that the features associated with different emotions are not exactly the same. Hence, traditional methods may fail to distinguish some of the emotions with just one global feature subspace. In this work, we propose a new divide and conquer idea to solve the problem. First, the feature subspaces are constructed for all the combinations of every two different emotions (emotion-pair). Bi-classifiers are then trained on these feature subspaces respectively. The final emotion recognition result is derived by the voting and competition method. Experimental results demonstrate that the proposed method can get better results than the traditional multi-classification method.

cs.LG↗

arXiv2013

Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition

In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm. Then we propose using a learned GRBM or MGRBM to extract better features for robust speech recognition. Our experiments on Aurora2 show that both GRBM-extracted and MGRBM-extracted feature performs much better than Mel-frequency cepstral coefficient (MFCC) with either HMM-GMM or hybrid HMM-deep neural network (DNN) acoustic model, and MGRBM-extracted feature is slightly better.

cs.CL↗