Add to Chrome
Add to Firefox
Add to EdgeUSAT: A Universal Speaker-Adaptive Text-to-Speech Approach
Apr 28, 2024
Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers, especially those with limited reference data, remains a significant and unresolved problem. While zero-shot or few-shot speaker-adaptive TTS approaches have been explored, they have many limitations. Zero-shot approaches tend to suffer from insufficient generalization performance to reproduce the voice of speakers with heavy accents. While few-shot methods can reproduce highly varying accents, they bring a significant storage burden and the risk of overfitting and catastrophic forgetting. In addition, prior approaches only provide either zero-shot or few-shot adaptation, constraining their utility across varied real-world scenarios with different demands. Besides, most current evaluations of speaker-adaptive TTS are conducted only on datasets of native speakers, inadvertently neglecting a vast portion of non-native speakers with diverse accents. Our proposed framework unifies both zero-shot and few-shot speaker adaptation strategies, which we term as "instant" and "fine-grained" adaptations based on their merits. To alleviate the insufficient generalization performance observed in zero-shot speaker adaptation, we designed two innovative discriminators and introduced a memory mechanism for the speech decoder. To prevent catastrophic forgetting and reduce storage implications for few-shot speaker adaptation, we designed two adapters and a unique adaptation procedure.
* 15 pages, 13 figures. Copyright has been transferred to IEEE
Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations
Aug 24, 2023
While most research into speech synthesis has focused on synthesizing high-quality speech for in-dataset speakers, an equally essential yet unsolved problem is synthesizing speech for unseen speakers who are out-of-dataset with limited reference data, i.e., speaker adaptive speech synthesis. Many studies have proposed zero-shot speaker adaptive text-to-speech and voice conversion approaches aimed at this task. However, most current approaches suffer from the degradation of naturalness and speaker similarity when synthesizing speech for unseen speakers (i.e., speakers not in the training dataset) due to the poor generalizability of the model in out-of-distribution data. To address this problem, we propose GZS-TV, a generalizable zero-shot speaker adaptive text-to-speech and voice conversion model. GZS-TV introduces disentangled representation learning for both speaker embedding extraction and timbre transformation to improve model generalization and leverages the representation learning capability of the variational autoencoder to enhance the speaker encoder. Our experiments demonstrate that GZS-TV reduces performance degradation on unseen speakers and outperforms all baseline models in multiple datasets.
AutoLV: Automatic Lecture Video Generator
Sep 19, 2022
We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video. Our system is primarily composed of a speech synthesis module with few-shot speaker adaptation and an adversarial learning-based talking-head generation module. It is capable of not only reducing instructors' workload but also changing the language and accent which can help the students follow the lecture more easily and enable a wider dissemination of lecture contents. Our experimental results show that the proposed model outperforms other current approaches in terms of authenticity, naturalness and accuracy. Here is a video demonstration of how our system works, and the outcomes of the evaluation and comparison: https://youtu.be/cY6TYkI0cog.
PhishSim: Aiding Phishing Website Detection with a Feature-Free Tool
Jul 13, 2022
In this paper, we propose a feature-free method for detecting phishing websites using the Normalized Compression Distance (NCD), a parameter-free similarity measure which computes the similarity of two websites by compressing them, thus eliminating the need to perform any feature extraction. It also removes any dependence on a specific set of website features. This method examines the HTML of webpages and computes their similarity with known phishing websites, in order to classify them. We use the Furthest Point First algorithm to perform phishing prototype extractions, in order to select instances that are representative of a cluster of phishing webpages. We also introduce the use of an incremental learning algorithm as a framework for continuous and adaptive detection without extracting new features when concept drift occurs. On a large dataset, our proposed method significantly outperforms previous methods in detecting phishing websites, with an AUC score of 98.68%, a high true positive rate (TPR) of around 90%, while maintaining a low false positive rate (FPR) of 0.58%. Our approach uses prototypes, eliminating the need to retain long term data in the future, and is feasible to deploy in real systems with a processing time of roughly 0.3 seconds.
* 34 pages, 20 figures
Fake News Quick Detection on Dynamic Heterogeneous Information Networks
May 14, 2022
The spread of fake news has caused great harm to society in recent years. So the quick detection of fake news has become an important task. Some current detection methods often model news articles and other related components as a static heterogeneous information network (HIN) and use expensive message-passing algorithms. However, in the real-world, quickly identifying fake news is of great significance and the network may vary over time in terms of dynamic nodes and edges. Therefore, in this paper, we propose a novel Dynamic Heterogeneous Graph Neural Network (DHGNN) for fake news quick detection. More specifically, we first implement BERT and fine-tuned BERT to get a semantic representation of the news article contents and author profiles and convert it into graph data. Then, we construct the heterogeneous news-author graph to reflect contextual information and relationships. Additionally, we adapt ideas from personalized PageRank propagation and dynamic propagation to heterogeneous networks in order to reduce the time complexity of back-propagating through many nodes during training. Experiments on three real-world fake news datasets show that DHGNN can outperform other GNN-based models in terms of both effectiveness and efficiency.
Man versus Machine: AutoML and Human Experts' Role in Phishing Detection
Aug 27, 2021
Machine learning (ML) has developed rapidly in the past few years and has successfully been utilized for a broad range of tasks, including phishing detection. However, building an effective ML-based detection system is not a trivial task, and requires data scientists with knowledge of the relevant domain. Automated Machine Learning (AutoML) frameworks have received a lot of attention in recent years, enabling non-ML experts in building a machine learning model. This brings to an intriguing question of whether AutoML can outperform the results achieved by human data scientists. Our paper compares the performances of six well-known, state-of-the-art AutoML frameworks on ten different phishing datasets to see whether AutoML-based models can outperform manually crafted machine learning models. Our results indicate that AutoML-based models are able to outperform manually developed machine learning models in complex classification tasks, specifically in datasets where the features are not quite discriminative, and datasets with overlapping classes or relatively high degrees of non-linearity. Challenges also remain in building a real-world phishing detection system using AutoML frameworks due to the current support only on supervised classification problems, leading to the need for labeled data, and the inability to update the AutoML-based models incrementally. This indicates that experts with knowledge in the domain of phishing and cybersecurity are still essential in the loop of the phishing detection pipeline.
Seirios: Leveraging Multiple Channels for LoRaWAN Indoor and Outdoor Localization
Aug 16, 2021
Localization is important for a large number of Internet of Things (IoT) endpoint devices connected by LoRaWAN. Due to the bandwidth limitations of LoRaWAN, existing localization methods without specialized hardware (e.g., GPS) produce poor performance. To increase the localization accuracy, we propose a super-resolution localization method, called Seirios, which features a novel algorithm to synchronize multiple non-overlapped communication channels by exploiting the unique features of the radio physical layer to increase the overall bandwidth. By exploiting both the original and the conjugate of the physical layer, Seirios can resolve the direct path from multiple reflectors in both indoor and outdoor environments. We design a Seirios prototype and evaluate its performance in an outdoor area of 100 m $\times$ 60 m, and an indoor area of 25 m $\times$ 15 m, which shows that Seirios can achieve a median error of 4.4 m outdoors (80% samples < 6.4 m), and 2.4 m indoors (80% samples < 6.1 m), respectively. The results show that Seirios produces 42% less localization error than the baseline approach. Our evaluation also shows that, different to previous studies in Wi-Fi localization systems that have wider bandwidth, time-of-fight (ToF) estimation is less effective for LoRaWAN localization systems with narrowband radio signals.
HaS-Nets: A Heal and Select Mechanism to Defend DNNs Against Backdoor Attacks for Data Collection Scenarios
Dec 14, 2020
We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). Most state-of-the-art defenses rely on the statistical sanitization of the "inputs" or "latent DNN representations" to capture trojan behaviour. In this paper, we first challenge the robustness of such recently reported defenses by introducing a novel variant of targeted backdoor attack, called "low-confidence backdoor attack". We also propose a novel defense technique, called "HaS-Nets". "Low-confidence backdoor attack" exploits the confidence labels assigned to poisoned training samples by giving low values to hide their presence from the defender, both during training and inference. We evaluate the attack against four state-of-the-art defense methods, viz., STRIP, Gradient-Shaping, Februus and ULP-defense, and achieve Attack Success Rate (ASR) of 99%, 63.73%, 91.2% and 80%, respectively. We next present "HaS-Nets" to resist backdoor insertion in the network during training, using a reasonably small healing dataset, approximately 2% to 15% of full training data, to heal the network at each iteration. We evaluate it for different datasets - Fashion-MNIST, CIFAR-10, Consumer Complaint and Urban Sound - and network architectures - MLPs, 2D-CNNs, 1D-CNNs. Our experiments show that "HaS-Nets" can decrease ASRs from over 90% to less than 15%, independent of the dataset, attack configuration and network architecture.
PhishZip: A New Compression-based Algorithm for Detecting Phishing Websites
Jul 22, 2020
Phishing has grown significantly in the past few years and is predicted to further increase in the future. The dynamics of phishing introduce challenges in implementing a robust phishing detection system and selecting features which can represent phishing despite the change of attack. In this paper, we propose PhishZip which is a novel phishing detection approach using a compression algorithm to perform website classification and demonstrate a systematic way to construct the word dictionaries for the compression models using word occurrence likelihood analysis. PhishZip outperforms the use of best-performing HTML-based features in past studies, with a true positive rate of 80.04%. We also propose the use of compression ratio as a novel machine learning feature which significantly improves machine learning based phishing detection over previous studies. Using compression ratios as additional features, the true positive rate significantly improves by 30.3% (from 51.47% to 81.77%), while the accuracy increases by 11.84% (from 71.20% to 83.04%).