arXiv subjects

Xixin Wu

Publications and source records attributed to Xixin Wu.

102 records · Page 6Linked to original sources

arXiv2021

Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks

Existing approaches for anti-spoofing in automatic speaker verification (ASV) still lack generalizability to unseen attacks. The Res2Net approach designs a residual-like connection between feature groups within one block, which increases the possible receptive fields and improves the system's detection generalizability. However, such a residual-like connection is performed by a direct addition between feature groups without channel-wise priority. We argue that the information across channels may not contribute to spoofing cues equally, and the less relevant channels are expected to be suppressed before adding onto the next feature group, so that the system can generalize better to unseen attacks. This argument motivates the current work that presents a novel, channel-wise gated Res2Net (CG-Res2Net), which modifies Res2Net to enable a channel-wise gating mechanism in the connection between feature groups. This gating mechanism dynamically selects channel-wise features based on the input, to suppress the less relevant channels and enhance the detection generalizability. Three gating mechanisms with different structures are proposed and integrated into Res2Net. Experimental results conducted on ASVspoof 2019 logical access (LA) demonstrate that the proposed CG-Res2Net significantly outperforms Res2Net on both the overall LA evaluation set and individual difficult unseen attacks, which also outperforms other state-of-the-art single systems, depicting the effectiveness of our method.

eess.AS↗

arXiv2021

VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis

This paper describes a variational auto-encoder based non-autoregressive text-to-speech (VAENAR-TTS) model. The autoregressive TTS (AR-TTS) models based on the sequence-to-sequence architecture can generate high-quality speech, but their sequential decoding process can be time-consuming. Recently, non-autoregressive TTS (NAR-TTS) models have been shown to be more efficient with the parallel decoding process. However, these NAR-TTS models rely on phoneme-level durations to generate a hard alignment between the text and the spectrogram. Obtaining duration labels, either through forced alignment or knowledge distillation, is cumbersome. Furthermore, hard alignment based on phoneme expansion can degrade the naturalness of the synthesized speech. In contrast, the proposed model of VAENAR-TTS is an end-to-end approach that does not require phoneme-level durations. The VAENAR-TTS model does not contain recurrent structures and is completely non-autoregressive in both the training and inference phases. Based on the VAE architecture, the alignment information is encoded in the latent variable, and attention-based soft alignment between the text and the latent variable is used in the decoder to reconstruct the spectrogram. Experiments show that VAENAR-TTS achieves state-of-the-art synthesis quality, while the synthesis speed is comparable with other NAR-TTS models.

cs.SD↗

arXiv2021

Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion

Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintaining speaker identity. To address this issue, we propose a VC system with explicit prosodic modelling and deep speaker embedding (DSE) learning. First, a speech-encoder strives to extract robust phoneme embeddings from atypical speech. Second, a prosody corrector takes in phoneme embeddings to infer typical phoneme duration and pitch values. Third, a conversion model takes phoneme embeddings and typical prosody features as inputs to generate the converted speech, conditioned on the target DSE that is learned via speaker encoder or speaker adaptation. Extensive experiments demonstrate that speaker adaptation can achieve higher speaker similarity, and the speaker encoder based conversion model can greatly reduce dysarthric and non-native pronunciation patterns with improved speech intelligibility. A comparison of speech recognition results between the original dysarthric speech and converted speech show that absolute reduction of 47.6% character error rate (CER) and 29.3% word error rate (WER) can be achieved.

eess.AS↗

arXiv2021

Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling

This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. During the training stage, an encoder-decoder-based hybrid connectionist-temporal-classification-attention (CTC-attention) phoneme recognizer is trained, whose encoder has a bottle-neck layer. A BNE is obtained from the phoneme recognizer and is utilized to extract speaker-independent, dense and rich spoken content representations from spectral features. Then a multi-speaker location-relative attention based seq2seq synthesis model is trained to reconstruct spectral features from the bottle-neck features, conditioning on speaker representations for speaker identity control in the generated speech. To mitigate the difficulties of using seq2seq models to align long sequences, we down-sample the input spectral feature along the temporal dimension and equip the synthesis model with a discretized mixture of logistic (MoL) attention mechanism. Since the phoneme recognizer is trained with large speech recognition data corpus, the proposed approach can conduct any-to-many voice conversion. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity. Ablation studies are conducted to confirm the effectiveness of feature selection and model design strategies in the proposed approach. The proposed VC approach can readily be extended to support any-to-any VC (also known as one/few-shot VC), and achieve high performance according to objective and subjective evaluations.

eess.AS↗

arXiv2021

Attention Forcing for Machine Translation

Auto-regressive sequence-to-sequence models with attention mechanisms have achieved state-of-the-art performance in various tasks including Text-To-Speech (TTS) and Neural Machine Translation (NMT). The standard training approach, teacher forcing, guides a model with the reference output history. At inference stage, the generated output history must be used. This mismatch can impact performance. However, it is highly challenging to train the model using the generated output. Several approaches have been proposed to address this problem, normally by selectively using the generated output history. To make training stable, these approaches often require a heuristic schedule or an auxiliary classifier. This paper introduces attention forcing for NMT. This approach guides the model with the generated output history and reference attention, and can reduce the training-inference mismatch without a schedule or a classifier. Attention forcing has been successful in TTS, but its application to NMT is more challenging, due to the discrete and multi-modal nature of the output space. To tackle this problem, this paper adds a selection scheme to vanilla attention forcing, which automatically selects a suitable training approach for each pair of training data. Experiments show that attention forcing can improve the overall translation quality and the diversity of the translations.

cs.CL↗

arXiv2021

Should Ensemble Members Be Calibrated?

Underlying the use of statistical approaches for a wide range of applications is the assumption that the probabilities obtained from a statistical model are representative of the "true" probability that event, or outcome, will occur. Unfortunately, for modern deep neural networks this is not the case, they are often observed to be poorly calibrated. Additionally, these deep learning approaches make use of large numbers of model parameters, motivating the use of Bayesian, or ensemble approximation, approaches to handle issues with parameter estimation. This paper explores the application of calibration schemes to deep ensembles from both a theoretical perspective and empirically on a standard image classification task, CIFAR-100. The underlying theoretical requirements for calibration, and associated calibration criteria, are first described. It is shown that well calibrated ensemble members will not necessarily yield a well calibrated ensemble prediction, and if the ensemble prediction is well calibrated its performance cannot exceed that of the average performance of the calibrated ensemble members. On CIFAR-100 the impact of calibration for ensemble prediction, and associated calibration is evaluated. Additionally the situation where multiple different topologies are combined together is discussed.

cs.LG↗

arXiv2020

Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization

Dysarthric speech recognition is a challenging task as dysarthric data is limited and its acoustics deviate significantly from normal speech. Model-based speaker adaptation is a promising method by using the limited dysarthric speech to fine-tune a base model that has been pre-trained from large amounts of normal speech to obtain speaker-dependent models. However, statistic distribution mismatches between the normal and dysarthric speech data limit the adaptation performance of the base model. To address this problem, we propose to re-initialize the base model via meta-learning to obtain a better model initialization. Specifically, we focus on end-to-end models and extend the model-agnostic meta learning (MAML) and Reptile algorithms to meta update the base model by repeatedly simulating adaptation to different dysarthric speakers. As a result, the re-initialized model acquires dysarthric speech knowledge and learns how to perform fast adaptation to unseen dysarthric speakers with improved performance. Experimental results on UASpeech dataset show that the best model with proposed methods achieves 54.2% and 7.6% relative word error rate reduction compared with the base model without finetuning and the model directly fine-tuned from the base model, respectively, and it is comparable with the state-of-the-art hybrid DNN-HMM model.

eess.AS↗

arXiv2020

Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification

Recently adversarial attacks on automatic speaker verification (ASV) systems attracted widespread attention as they pose severe threats to ASV systems. However, methods to defend against such attacks are limited. Existing approaches mainly focus on retraining ASV systems with adversarial data augmentation. Also, countermeasure robustness against different attack settings are insufficiently investigated. Orthogonal to prior approaches, this work proposes to defend ASV systems against adversarial attacks with a separate detection network, rather than augmenting adversarial data into ASV training. A VGG-like binary classification detector is introduced and demonstrated to be effective on detecting adversarial samples. To investigate detector robustness in a realistic defense scenario where unseen attack settings may exist, we analyze various kinds of unseen attack settings' impact and observe that the detector is robust (6.27\% EER_{det} degradation in the worst case) against unseen substitute ASV systems, but it has weak robustness (50.37\% EER_{det} degradation in the worst case) against unseen perturbation methods. The weak robustness against unseen perturbation methods shows a direction for developing stronger countermeasures.

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

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↗

arXiv2019

Maximizing Mutual Information for Tacotron

End-to-end speech synthesis methods already achieve close-to-human quality performance. However compared to HMM-based and NN-based frame-to-frame regression methods, they are prone to some synthesis errors, such as missing or repeating words and incomplete synthesis. We attribute the comparatively high utterance error rate to the local information preference of conditional autoregressive models, and the ill-posed training objective of the model, which describes mostly the training status of the autoregressive module, but rarely that of the condition module. Inspired by InfoGAN, we propose to maximize the mutual information between the text condition and the predicted acoustic features to strengthen the dependency between them for CAR speech synthesis model, which would alleviate the local information preference issue and reduce the utterance error rate. The training objective of maximizing mutual information can be considered as a metric of the dependency between the autoregressive module and the condition module. Experiment results show that our method can reduce the utterance error rate.

eess.AS↗