May 6, 2019

2743 words 13 mins read

Paper Group ANR 281

Speaker Cluster-Based Speaker Adaptive Training for Deep Neural Network Acoustic Modeling. Online Trajectory Segmentation and Summary With Applications to Visualization and Retrieval. Sparse Convex Clustering. Weakly Supervised PLDA Training. Technical Report: Directed Controller Synthesis of Discrete Event Systems. Bit-Planes: Dense Subpixel Align …

Speaker Cluster-Based Speaker Adaptive Training for Deep Neural Network Acoustic Modeling


Title	Speaker Cluster-Based Speaker Adaptive Training for Deep Neural Network Acoustic Modeling
Authors	Wei Chu, Ruxin Chen
Abstract	A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DNNs with speaker dependent layers are then adaptively trained for each cluster of speakers. Before decoding starts, an unseen speaker in test set is matched to the closest speaker cluster through comparing i-vector based distances. The previously trained DNN of the matched speaker cluster is used for decoding utterances of the test speaker. The performance of the proposed method on a large vocabulary spontaneous speech recognition task is evaluated on a training set of with 1500 hours of speech, and a test set of 24 speakers with 1774 utterances. Comparing to a speaker independent DNN with a baseline word error rate of 11.6%, a relative 6.8% reduction in word error rate is observed from the proposed method.
Tasks	Speech Recognition
Published	2016-04-20
URL	http://arxiv.org/abs/1604.06113v1
PDF	http://arxiv.org/pdf/1604.06113v1.pdf
PWC	https://paperswithcode.com/paper/speaker-cluster-based-speaker-adaptive
Repo
Framework

Online Trajectory Segmentation and Summary With Applications to Visualization and Retrieval


Title	Online Trajectory Segmentation and Summary With Applications to Visualization and Retrieval
Authors	Yehezkel S. Resheff
Abstract	Trajectory segmentation is the process of subdividing a trajectory into parts either by grouping points similar with respect to some measure of interest, or by minimizing a global objective function. Here we present a novel online algorithm for segmentation and summary, based on point density along the trajectory, and based on the nature of the naturally occurring structure of intermittent bouts of locomotive and local activity. We show an application to visualization of trajectory datasets, and discuss the use of the summary as an index allowing efficient queries which are otherwise impossible or computationally expensive, over very large datasets.
Tasks
Published	2016-07-24
URL	http://arxiv.org/abs/1607.08188v1
PDF	http://arxiv.org/pdf/1607.08188v1.pdf
PWC	https://paperswithcode.com/paper/online-trajectory-segmentation-and-summary
Repo
Framework

Sparse Convex Clustering


Title	Sparse Convex Clustering
Authors	Binhuan Wang, Yilong Zhang, Will Wei Sun, Yixin Fang
Abstract	Convex clustering, a convex relaxation of k-means clustering and hierarchical clustering, has drawn recent attentions since it nicely addresses the instability issue of traditional nonconvex clustering methods. Although its computational and statistical properties have been recently studied, the performance of convex clustering has not yet been investigated in the high-dimensional clustering scenario, where the data contains a large number of features and many of them carry no information about the clustering structure. In this paper, we demonstrate that the performance of convex clustering could be distorted when the uninformative features are included in the clustering. To overcome it, we introduce a new clustering method, referred to as Sparse Convex Clustering, to simultaneously cluster observations and conduct feature selection. The key idea is to formulate convex clustering in a form of regularization, with an adaptive group-lasso penalty term on cluster centers. In order to optimally balance the tradeoff between the cluster fitting and sparsity, a tuning criterion based on clustering stability is developed. In theory, we provide an unbiased estimator for the degrees of freedom of the proposed sparse convex clustering method. Finally, the effectiveness of the sparse convex clustering is examined through a variety of numerical experiments and a real data application.
Tasks	Feature Selection
Published	2016-01-18
URL	http://arxiv.org/abs/1601.04586v4
PDF	http://arxiv.org/pdf/1601.04586v4.pdf
PWC	https://paperswithcode.com/paper/sparse-convex-clustering
Repo
Framework

Weakly Supervised PLDA Training


Title	Weakly Supervised PLDA Training
Authors	Lantian Li, Yixiang Chen, Dong Wang, Chenghui Zhao
Abstract	PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labelled development data, which is highly expensive in most cases. We present a cheap PLDA training approach, which assumes that speakers in the same session can be easily separated, and speakers in different sessions are simply different. This results in `weak labels’ which are not fully accurate but cheap, leading to a weak PLDA training. Our experimental results on real-life large-scale telephony customer service achieves demonstrated that the weak training can offer good performance when human-labelled data are limited. More interestingly, the weak training can be employed as a discriminative adaptation approach, which is more efficient than the prevailing unsupervised method when human-labelled data are insufficient. \|
Tasks	Speaker Verification
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08441v2
PDF	http://arxiv.org/pdf/1609.08441v2.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-plda-training
Repo
Framework

Technical Report: Directed Controller Synthesis of Discrete Event Systems


Title	Technical Report: Directed Controller Synthesis of Discrete Event Systems
Authors	Daniel Ciolek, Victor Braberman, Nicolás D’Ippolito, Sebastián Uchitel
Abstract	This paper presents a Directed Controller Synthesis (DCS) technique for discrete event systems. The DCS method explores the solution space for reactive controllers guided by a domain-independent heuristic. The heuristic is derived from an efficient abstraction of the environment based on the componentized way in which complex environments are described. Then by building the composition of the components on-the-fly DCS obtains a solution by exploring a reduced portion of the state space. This work focuses on untimed discrete event systems with safety and co-safety (i.e. reachability) goals. An evaluation for the technique is presented comparing it to other well-known approaches to controller synthesis (based on symbolic representation and compositional analyses).
Tasks
Published	2016-05-31
URL	http://arxiv.org/abs/1605.09772v1
PDF	http://arxiv.org/pdf/1605.09772v1.pdf
PWC	https://paperswithcode.com/paper/technical-report-directed-controller
Repo
Framework

Bit-Planes: Dense Subpixel Alignment of Binary Descriptors


Title	Bit-Planes: Dense Subpixel Alignment of Binary Descriptors
Authors	Hatem Alismail, Brett Browning, Simon Lucey
Abstract	Binary descriptors have been instrumental in the recent evolution of computationally efficient sparse image alignment algorithms. Increasingly, however, the vision community is interested in dense image alignment methods, which are more suitable for estimating correspondences from high frame rate cameras as they do not rely on exhaustive search. However, classic dense alignment approaches are sensitive to illumination change. In this paper, we propose an easy to implement and low complexity dense binary descriptor, which we refer to as bit-planes, that can be seamlessly integrated within a multi-channel Lucas & Kanade framework. This novel approach combines the robustness of binary descriptors with the speed and accuracy of dense alignment methods. The approach is demonstrated on a template tracking problem achieving state-of-the-art robustness and faster than real-time performance on consumer laptops (400+ fps on a single core Intel i7) and hand-held mobile devices (100+ fps on an iPad Air 2).
Tasks
Published	2016-01-31
URL	http://arxiv.org/abs/1602.00307v1
PDF	http://arxiv.org/pdf/1602.00307v1.pdf
PWC	https://paperswithcode.com/paper/bit-planes-dense-subpixel-alignment-of-binary
Repo
Framework

Prioritised Default Logic as Argumentation with Partial Order Default Priorities


Title	Prioritised Default Logic as Argumentation with Partial Order Default Priorities
Authors	Anthony P. Young, Sanjay Modgil, Odinaldo Rodrigues
Abstract	We express Brewka’s prioritised default logic (PDL) as argumentation using ASPIC+. By representing PDL as argumentation and designing an argument preference relation that takes the argument structure into account, we prove that the conclusions of the justified arguments correspond to the PDL extensions. We will first assume that the default priority is total, and then generalise to the case where it is a partial order. This provides a characterisation of non-monotonic inference in PDL as an exchange of argument and counter-argument, providing a basis for distributed non-monotonic reasoning in the form of dialogue.
Tasks
Published	2016-08-25
URL	http://arxiv.org/abs/1609.05224v1
PDF	http://arxiv.org/pdf/1609.05224v1.pdf
PWC	https://paperswithcode.com/paper/prioritised-default-logic-as-argumentation
Repo
Framework

When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter


Title	When silver glitters more than gold: Bootstrapping an Italian part-of-speech tagger for Twitter
Authors	Barbara Plank, Malvina Nissim
Abstract	We bootstrap a state-of-the-art part-of-speech tagger to tag Italian Twitter data, in the context of the Evalita 2016 PoSTWITA shared task. We show that training the tagger on native Twitter data enriched with little amounts of specifically selected gold data and additional silver-labelled data scraped from Facebook, yields better results than using large amounts of manually annotated data from a mix of genres.
Tasks
Published	2016-11-09
URL	http://arxiv.org/abs/1611.03057v1
PDF	http://arxiv.org/pdf/1611.03057v1.pdf
PWC	https://paperswithcode.com/paper/when-silver-glitters-more-than-gold
Repo
Framework

An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax


Title	An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax
Authors	Wentao Huang, Kechen Zhang
Abstract	A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon’s mutual information for a large neural population to demonstrate that a good initial approximation to the global information-theoretic optimum can be obtained by a hierarchical infomax method. Starting from the initial solution, an efficient algorithm based on gradient descent of the final objective function is proposed to learn representations from the input datasets, and the method works for complete, overcomplete, and undercomplete bases. As confirmed by numerical experiments, our method is robust and highly efficient for extracting salient features from input datasets. Compared with the main existing methods, our algorithm has a distinct advantage in both the training speed and the robustness of unsupervised representation learning. Furthermore, the proposed method is easily extended to the supervised or unsupervised model for training deep structure networks.
Tasks	Representation Learning, Unsupervised Representation Learning
Published	2016-11-07
URL	http://arxiv.org/abs/1611.01886v4
PDF	http://arxiv.org/pdf/1611.01886v4.pdf
PWC	https://paperswithcode.com/paper/an-information-theoretic-framework-for-fast
Repo
Framework

Instance-sensitive Fully Convolutional Networks


Title	Instance-sensitive Fully Convolutional Networks
Authors	Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun
Abstract	Fully convolutional networks (FCNs) have been proven very successful for semantic segmentation, but the FCN outputs are unaware of object instances. In this paper, we develop FCNs that are capable of proposing instance-level segment candidates. In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances. On top of these instance-sensitive score maps, a simple assembling module is able to output instance candidate at each position. In contrast to the recent DeepMask method for segmenting instances, our method does not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances. We present competitive results of instance segment proposal on both PASCAL VOC and MS COCO.
Tasks	Semantic Segmentation
Published	2016-03-29
URL	http://arxiv.org/abs/1603.08678v1
PDF	http://arxiv.org/pdf/1603.08678v1.pdf
PWC	https://paperswithcode.com/paper/instance-sensitive-fully-convolutional
Repo
Framework


Title	The Social Dynamics of Language Change in Online Networks
Authors	Rahul Goel, Sandeep Soni, Naman Goyal, John Paparrizos, Hanna Wallach, Fernando Diaz, Jacob Eisenstein
Abstract	Language change is a complex social phenomenon, revealing pathways of communication and sociocultural influence. But, while language change has long been a topic of study in sociolinguistics, traditional linguistic research methods rely on circumstantial evidence, estimating the direction of change from differences between older and younger speakers. In this paper, we use a data set of several million Twitter users to track language changes in progress. First, we show that language change can be viewed as a form of social influence: we observe complex contagion for phonetic spellings and “netspeak” abbreviations (e.g., lol), but not for older dialect markers from spoken language. Next, we test whether specific types of social network connections are more influential than others, using a parametric Hawkes process model. We find that tie strength plays an important role: densely embedded social ties are significantly better conduits of linguistic influence. Geographic locality appears to play a more limited role: we find relatively little evidence to support the hypothesis that individuals are more influenced by geographically local social ties, even in their usage of geographical dialect markers.
Tasks
Published	2016-09-07
URL	http://arxiv.org/abs/1609.02075v1
PDF	http://arxiv.org/pdf/1609.02075v1.pdf
PWC	https://paperswithcode.com/paper/the-social-dynamics-of-language-change-in
Repo
Framework

Towards Representation Learning with Tractable Probabilistic Models


Title	Towards Representation Learning with Tractable Probabilistic Models
Authors	Antonio Vergari, Nicola Di Mauro, Floriana Esposito
Abstract	Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be computed in polynomial time, can enable general schemes to extract features from black box models. We plan to investigate how Tractable Probabilistic Models (TPMs) can be exploited to generate embeddings by random query evaluations. We devise two experimental designs to assess and compare different TPMs as feature extractors in an unsupervised representation learning framework. We show some experimental results on standard image datasets by applying such a method to Sum-Product Networks and Mixture of Trees as tractable models generating embeddings.
Tasks	Representation Learning, Unsupervised Representation Learning
Published	2016-08-08
URL	http://arxiv.org/abs/1608.02341v1
PDF	http://arxiv.org/pdf/1608.02341v1.pdf
PWC	https://paperswithcode.com/paper/towards-representation-learning-with
Repo
Framework

Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis


Title	Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis
Authors	Andreas Damianou, Neil D. Lawrence, Carl Henrik Ek
Abstract	Factor analysis aims to determine latent factors, or traits, which summarize a given data set. Inter-battery factor analysis extends this notion to multiple views of the data. In this paper we show how a nonlinear, nonparametric version of these models can be recovered through the Gaussian process latent variable model. This gives us a flexible formalism for multi-view learning where the latent variables can be used both for exploratory purposes and for learning representations that enable efficient inference for ambiguous estimation tasks. Learning is performed in a Bayesian manner through the formulation of a variational compression scheme which gives a rigorous lower bound on the log likelihood. Our Bayesian framework provides strong regularization during training, allowing the structure of the latent space to be determined efficiently and automatically. We demonstrate this by producing the first (to our knowledge) published results of learning from dozens of views, even when data is scarce. We further show experimental results on several different types of multi-view data sets and for different kinds of tasks, including exploratory data analysis, generation, ambiguity modelling through latent priors and classification.
Tasks	MULTI-VIEW LEARNING
Published	2016-04-17
URL	http://arxiv.org/abs/1604.04939v1
PDF	http://arxiv.org/pdf/1604.04939v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-learning-as-a-nonparametric
Repo
Framework

Iterated Ontology Revision by Reinterpretation


Title	Iterated Ontology Revision by Reinterpretation
Authors	Özgür Lütfü Özçep
Abstract	Iterated applications of belief change operators are essential for different scenarios such as that of ontology evolution where new information is not presented at once but only in piecemeal fashion within a sequence. I discuss iterated applications of so called reinterpretation operators that trace conflicts between ontologies back to the ambiguous of symbols and that provide conflict resolution strategies with bridging axioms. The discussion centers on adaptations of the classical iteration postulates according to Darwiche and Pearl. The main result of the paper is that reinterpretation operators fulfill the postulates for sequences containing only atomic triggers. For complex triggers, a fulfillment is not guaranteed and indeed there are different reasons for the different postulates why they should not be fulfilled in the particular scenario of ontology revision with well developed ontologies.
Tasks
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09194v1
PDF	http://arxiv.org/pdf/1603.09194v1.pdf
PWC	https://paperswithcode.com/paper/iterated-ontology-revision-by
Repo
Framework

Preference Completion from Partial Rankings


Title	Preference Completion from Partial Rankings
Authors	Suriya Gunasekar, Oluwasanmi Koyejo, Joydeep Ghosh
Abstract	We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of observed affinity values. Our approach exploits the observation that while preferences are often recorded as numerical scores, the predictive quantity of interest is the underlying rankings. Thus, attempts to closely match the recorded scores may lead to overfitting and impair generalization performance. Instead, we propose an estimator that directly fits the underlying preference order, combined with nuclear norm constraints to encourage low–rank parameters. Besides (approximate) correctness of the ranking order, the proposed estimator makes no generative assumption on the numerical scores of the observations. One consequence is that the proposed estimator can fit any consistent partial ranking over a subset of the items represented as a directed acyclic graph (DAG), generalizing standard techniques that can only fit preference scores. Despite this generality, for supervision representing total or blockwise total orders, the computational complexity of our algorithm is within a $\log$ factor of the standard algorithms for nuclear norm regularization based estimates for matrix completion. We further show promising empirical results for a novel and challenging application of collaboratively ranking of the associations between brain–regions and cognitive neuroscience terms.
Tasks	Matrix Completion
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04218v1
PDF	http://arxiv.org/pdf/1611.04218v1.pdf
PWC	https://paperswithcode.com/paper/preference-completion-from-partial-rankings
Repo
Framework