Abstract

Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and time-consuming. In this paper different styles of speech are analysed based on prosodic variations, from this a model is proposed to synthesise speech in the style of a newscaster, with just a few hours of supplementary data. We pose the problem of synthesising in a target style using limited data as that of creating a bi-style model that can synthesise both neutral-style and newscaster-style speech via a one-hot vector which factorises the two styles. We also propose conditioning the model on contextual word embeddings, and extensively evaluate it against neutral NTTS, and neutral concatenative-based synthesis. This model closes the gap in perceived style-appropriateness between natural recordings for newscaster-style of speech, and neutral speech synthesis by approximately two-thirds.

Abstract

Musical training causes structural and functional changes in the brain due to its sensory-motor demands. This leads to differences in how musicians perceive and process music as compared to nonmusicians, thereby providing insights into brain adaptations and plasticity. Correlational studies and network analysis investigations have indicated the presence of large-scale brain networks involved in the processing of music and have highlighted the differences between musicians and non-musicians. However, studies on functional connectivity in the brain during music listening tasks have thus far focused solely on static network analysis. Dynamic Functional Connectivity (DFC) studies have lately been found useful in unearthing meaningful, time-varying functional connectivity information in both resting-state and task-based experimental settings. In this study, we examine DFC in the fMRI obtained from two groups of participants, 18 musicians and 18 non-musicians, while they listened to a musical stimulus in a naturalistic setting. We utilize spatial Group Independent Component Analysis (ICA), sliding time window correlations, and a deterministic agglomerative clustering of windowed correlation matrices to identify quasi-stable Functional Connectivity (FC) states in the two groups. To compute cluster centroids that represent FC states, we device and present a method that primarily utilizes windowed correlation matrices occurring repeatedly over time and across participants, while excluding matrices corresponding to spontaneous fluctuations. Preliminary analysis indicate states with greater visuo-sensorimotor integration in musicians, larger presence of DMN states in non-musicians, and variability in states found in musicians due to differences in training and prior experiences.

Abstract

. Automatic research paper summarization is a fairly interesting topic that has garnered significant interest in the research community in recent years. In this paper, we introduce team Helium’s system description for the CL-SciSumm shared task colocated with SIGIR 2019. We specifically attempt the first task, targeting in building an improved recall system of reference text spans from a given citing research paper (Task 1A) and constructing better models for comprehension of scientific facets (Task 1B). Our architecture incorporates transfer learning by utilising a combination of pretrained embeddings which are subsequently used for building models for the given tasks. In particular - for task 1A, we locate the related text spans referred to by the citation text by creating paired text representations and employ pre-trained embedding mechanisms in conjunction with XGBoost, a gradient boosted decision tree algorithm to identify textual entailment. For task 1B, we make use of the same pretrained embeddings and use the RAKEL algorithm for multi-label classification. Our goal is to enable better scientific research comprehension and we believe that a new approach involving transfer learning will certainly add value to the research community working on these tasks.

Abstract

No Results Found

Abstract

We introduce a novel model for future/next page prediction in on- line user journeys that uses a combination of doc2vec webpage representations with an LSTM-based neural network to mine pat- terns from users’ online navigational paths combined with their content preferences. Empirical explorations show promise towards creating customized user experiences leveraging this work.

Abstract

In this paper, the problem of path planning through tight spaces, for the task of spatial payload transportation, using a formation of mobile manipulators is addressed. Due to the high dimensional configuration space of the system, efficient and geometrically stable path planning through tight spaces is challenging. We resolve this by planning the path for the system in two phases. First, an obstacle-free trajectory in R 3 for the payload being transported is determined using RRT. Next, near-energy optimal and quasi-statically stable paths are planned for the formation of robots along this trajectory using non-linear multi-objective optimization. We validate the proposed approach in simulation experiments and compare different multi-objective optimization algorithms to find energy optimal and geometrically stable robot path plans.

Abstract

In the field of hyperspectral remote sensing, the spectral data is derived from hyperspectral images and are matched with the spectral library. Till date there are no studies that have matched with the hand–held spectrum collected by spectroradiometer at temporal scale. Creating a spectral library for the same species at various regions is a challenge, as acquiring spectrum at temporal sets are practically difficult and expensive. The absorption features are the unique key print for the identification of the two different samples of same species and also helps to discriminate two different species. The intensity and position of strong absorption region helps to match the spectrum accurately. In the current study probability based matching technique is used where the dips of a species of a season is matched to the other within a predefined abundance window. This study helps to know the seasonal changes of the tree due to its environmental factors, stress and deficiency.

Abstract

In this work we introduce the task of item recommendation in an aggregated marketplace. An aggregated market place is a single place where items from multiple e-commerce sites can be viewed and compared. Our main objective while recommending items is to provide users with alternatives across different e-commerce sites. To accomplish this, we embed items in a vector space and apply retrofitting, a method used in language processing to inject relationships into word embeddings. Due to recent attention towards item recommendation using only click data without any user feedback and our particular constraints, we test our model on real click data derived from Samsung Mall App.

Abstract

Social network and publishing platforms, such as Twitter, support the concept of verification. Verified accounts are deemed worthy of platform-wide public interest and are separately authenticated by the platform itself. There have been repeated assertions by these platforms about verification not being tantamount to endorsement. However, a significant body of prior work suggests that possessing a verified status symbolizes enhanced credibility in the eyes of the platform audience. As a result, such a status is highly coveted among public figures and influencers. Hence, we attempt to characterize the network of verified users on Twitter and compare the results to similar analysis performed for the entire Twitter network. We extracted the entire network of verified users on Twitter (as of July 2018) and obtained 231,246 English user profiles and 79,213,811 connections. Subsequently, in the network analysis, we found that the sub-graph of verified users mirrors the full Twitter users graph in some aspects such as possessing a short diameter. However, our findings contrast with earlier findings on multiple aspects, such as the possession of a power law out- degree distribution, slight dissortativity, and a significantly higher reciprocity rate, as elucidated in the paper. Moreover, we attempt to gauge the presence of salient components within this sub-graph and detect the absence of homophily with respect to popularity, which again is in stark contrast to the full Twitter graph. Finally, we demonstrate stationarity in the time series of verified user activity levels. To the best of our knowledge, this work represents the first quantitative attempt at characterizing verified users on Twitter. Index Terms—Twitter, Social Influence, Centrality, Network Analysis, Online User Characterization, User Categorization

Abstract

Stack Overflow, a Q&A site on programming, awards reputation points and badges (game elements) to users on performing various actions. Situating our work in Digital Signaling Theory, we investigate the role of these game elements in characterizing social qualities (specifically, popularity and impact) of its users. We operationalize these attributes using common metrics and apply statistical modeling to empirically quantify and validate the strength of these signals. Our results are based on a rich dataset of 3,831,147 users and their activities spanning nearly a decade since the site's inception in 2008. We present evidence that certain non-trivial badges, reputation scores and age of the user on the site positively correlate with popularity and impact. Further, we find that the presence of costly to earn and hard to observe signals qualitatively differentiates highly impactful users from highly popular users.