Wei Zhang

The multivariate time series generated from merchant transaction history can provide critical insights for payment processing companies. The capability of predicting merchants’ future is crucial for fraud detection and recommendation systems. Conventionally, this problem is formulated to predict one multivariate time series under the multi-horizon setting. However, real-world applications often require more than one future trend prediction considering the uncertainties, where more than one… Show more

The multivariate time series generated from merchant transaction history can provide critical insights for payment processing companies. The capability of predicting merchants’ future is crucial for fraud detection and recommendation systems. Conventionally, this problem is formulated to predict one multivariate time series under the multi-horizon setting. However, real-world applications often require more than one future trend prediction considering the uncertainties, where more than one multivariate time series needs to be predicted. This problem is called multi-future prediction. In this work, we combine the two research directions and propose to study this new problem: multi-future, multi-horizon and multivariate time series prediction. This problem is crucial as it has broad use cases in the financial industry to reduce the risk while improving user experience by providing alternative futures. This problem is also challenging as now we not only need to capture the patterns and insights from the past but also train a model that has a strong inference capability to project multiple possible outcomes. To solve this problem, we propose a new model using convolutional neural networks and a simple yet effective encoder-decoder structure to learn the time series pattern from multiple perspectives. We use experiments on real-world merchant transaction data to demonstrate the effectiveness of our proposed model. We also provide extensive discussions on different model design choices in our experimental section. Show less

REACH is an intelligent, people-finding system that helps users to find someone in their social directory, especially those whom they do not fully remember or barely know. It analyzes a user’s communication and social networking data to automatically extract all the contacts and derive multiple facets to characterize each contact in relation to the user. It then employs a personalized, faceted search to retrieve and present a ranked list of matched contacts based on their properties. A… Show more

REACH is an intelligent, people-finding system that helps users to find someone in their social directory, especially those whom they do not fully remember or barely know. It analyzes a user’s communication and social networking data to automatically extract all the contacts and derive multiple facets to characterize each contact in relation to the user. It then employs a personalized, faceted search to retrieve and present a ranked list of matched contacts based on their properties. A preliminary evaluation shows the effectiveness of our approach. Show less

This paper presents an approach using phonetic context similarity as a cost function in unit selection of concatenative Text-to- Speech. The approach measures the degree of similarity between the desired context and the candidate segment under different phonetic contexts. It considers the impact from relatively far contexts when plenty of candidates are available and can take advantage of the data from other symbolically different contexts when the candidates are sparse. Moreover, the cost… Show more

This paper presents an approach using phonetic context similarity as a cost function in unit selection of concatenative Text-to- Speech. The approach measures the degree of similarity between the desired context and the candidate segment under different phonetic contexts. It considers the impact from relatively far contexts when plenty of candidates are available and can take advantage of the data from other symbolically different contexts when the candidates are sparse. Moreover, the cost function also provides an efficient way to prune the search space. Different parameters for modeling, normalization and integerization are discussed. MOS evaluation shows that it can improve the synthesis quality significantly. Show less

The work presented in this paper is subsequent to the paper “Probability Based Prosody Model for Unit Selection” which was published in ICASSP'2004. In the improved probability prosody model for corpus based concatenative Text-to-Speech (TTS), likelihood is replaced with posterior probability in the cost functions which conduct the following step, unit selection. Objective and subjective experiments show that posterior probability has obvious advantages over likelihood on robustness… Show more

The work presented in this paper is subsequent to the paper “Probability Based Prosody Model for Unit Selection” which was published in ICASSP'2004. In the improved probability prosody model for corpus based concatenative Text-to-Speech (TTS), likelihood is replaced with posterior probability in the cost functions which conduct the following step, unit selection. Objective and subjective experiments show that posterior probability has obvious advantages over likelihood on robustness, flexibility and overall quality. Show less