Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high computational complexity and irregular structures are still considered challenging concerns, which yield a variety of voice quality degradation. Therefore, this paper presents new techniques in a continuous vocoder, that is all features are continuous and presents a flexible speech synthesis system. First, a new continuous noise masking based on the phase distortion is proposed to eliminate the perceptual impact of the residual noise and letting an accurate reconstruction of noise characteristics. Second, we addressed the need of neural sequence to sequence modeling approach for the task of TTS based on recurrent networks. Bidirectional long short-term memory (LSTM) and gated recurrent unit (GRU) are studied and applied to model continuous parameters for more natural-sounding like a human. The evaluation results proved that the proposed model achieves the state-of-the-art performance of the speech synthesis compared with the other traditional methods.

This paper presents TS2Vec, a universal framework for learning timestamp-level representations of time series. Unlike existing methods, TS2Vec performs timestamp-wise discrimination, which learns a contextual representation vector directly for each timestamp. We find that the learned representations have superior predictive ability. A linear regression trained on top of the learned representations outperforms previous SOTAs for supervised time series forecasting. Also, the instance-level representations can be simply obtained by applying a max pooling layer on top of learned representations of all timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of instance-level representations. As a result, TS2Vec achieves significant improvement compared with existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The source code is publicly available at https://github.com/yuezhihan/ts2vec.

Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal grounding between language and vision information. We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question's intentions. MASN consists of a motion module, an appearance module, and a motion-appearance fusion module. The motion module computes the action-oriented cross-modal joint representations, while the appearance module focuses on the appearance aspect of the input video. Finally, the motion-appearance fusion module takes each output of the motion module and the appearance module as input, and performs question-guided fusion. As a result, MASN achieves new state-of-the-art performance on the TGIF-QA and MSVD-QA datasets. We also conduct qualitative analysis by visualizing the inference results of MASN. The code is available at https://github.com/ahjeongseo/MASN-pytorch.

The neural network and quantum computing are both significant and appealing fields, with their interactive disciplines promising for large-scale computing tasks that are untackled by conventional computers. However, both developments are restricted by the scope of the hardware development. Nevertheless, many neural network algorithms had been proposed before GPUs become powerful enough for running very deep models. Similarly, quantum algorithms can also be proposed as knowledge reserves before real quantum computers are easily accessible. Specifically, taking advantage of both the neural networks and quantum computation and designing quantum deep neural networks (QDNNs) for acceleration on Noisy Intermediate-Scale Quantum (NISQ) processors is also an important research problem. As one of the most widely used neural network architectures, convolutional neural network (CNN) remains to be accelerated by quantum mechanisms, with only a few attempts have been demonstrated. In this paper, we propose a new hybrid quantum-classical circuit, namely Quantum Fourier Convolutional Network (QFCN). Our model achieves exponential speed-up compared with classical CNN theoretically and improves over the existing best result of quantum CNN. We demonstrate the potential of this architecture by applying it to different deep learning tasks, including traffic prediction and image classification.

Many real-world systems can be expressed in temporal networks with nodes playing far different roles in structure and function and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread of public opinions or epidemics, predict leading figures in academia, conduct advertisements for various commodities, and so on. However, it is rather difficult to identify critical nodes because the network structure changes over time in temporal networks. In this paper, considering the sequence topological information of temporal networks, a novel and effective learning framework based on the combination of special GCNs and RNNs is proposed to identify nodes with the best spreading ability. The effectiveness of the approach is evaluated by weighted Susceptible-Infected-Recovered model. Experimental results on four real-world temporal networks demonstrate that the proposed method outperforms both traditional and deep learning benchmark methods in terms of the Kendall $\tau$ coefficient and top $k$ hit rate.

Machine programming, which automates the development and maintenance of software, is becoming supercharged by AI. During its Build developer conference in May, Microsoft detailed a new feature in Power Apps that taps OpenAI's GPT-3 language model to assist people in choosing formulas. Intel's ControlFlag can autonomously detect errors in code. And Facebook's TransCoder converts code from one programming language into another. The applications of computer programming are vast in scope.

Machine learning (ML) is a branch of artificial intelligence (AI) that enables computers to self-learn and improve over time without being explicitly programmed. In short, machine learning algorithms are able to detect and learn from patterns in data and make their own predictions. In traditional programming, someone writes a series of instructions so that a computer can transform input data into a desired output. Instructions are mostly based on an IF-THEN structure: when certain conditions are met, the program executes a specific action. Machine learning, on the other hand, is an automated process that enables machines to solve problems and take actions based on past observations.

The field of Artificial Intelligence (AI) is no stranger to prophesy. At the Ford Distinguished Lectures in 1960, the economist Herbert Simon declared that within 20 years machines would be capable of performing any task achievable by humans. In 1961, Claude Shannon -- the founder of information theory -- predicted that science fiction style robots would emerge within 15 years. Good conceived of a runaway "intelligence explosion," a process whereby smarter-than-human machines iteratively improve their own intelligence. Writing in 1965, Good predicted that the explosion would arrive before the end of the twentieth century.

Mitigating the effects of disease outbreaks with timely and effective interventions requires accurate real-time surveillance and forecasting of disease activity, but traditional health care–based surveillance systems are limited by inherent reporting delays. Machine learning methods have the potential to fill this temporal “data gap,” but work to date in this area has focused on relatively simple methods and coarse geographic resolutions (state level and above). We evaluate the predictive performance of a gated recurrent unit neural network approach in comparison with baseline machine learning methods for estimating influenza activity in the United States at the state and city levels and experiment with the inclusion of real-time Internet search data. We find that the neural network approach improves upon baseline models for long time horizons of prediction but is not improved by real-time internet search data. We conduct a thorough analysis of feature importances in all considered models for interpretability purposes.

If you're wondering, who am I to tell you anything about GPT-3 AI? Well, I'm Lillian Pierson, and I help data professionals become world-class data leaders and entrepreneurs - to date I've trained over 1 million data professionals on the topics of data science and AI. I'm a data scientist turned data entrepreneur, and I've been testing out GPT-3 AI for about 3 months now in my data business, Data-Mania.