Sharif Digital Repository

The key element of a spoken dialogue system is a spoken language understanding (SLU) unit. Hidden Vector State (HVS) is one of the most popular statistical approaches employed to implement the SLU unit. This paper presents a two-step approach for Persian language understanding. First, a goal detector is used to identify the main goal of the input utterance. Second, after restricting the search space for semantic tagging, an extended hidden vector state (EHVS) parser is used to extract the remaining semantics in each subspace. This will mainly improve the performance of semantic tagger, while reducing the model complexity and training time. Moreover, the need for large amount of data will be... 

In this paper, we aim to improve meeting summarization performance using discourse specific information. Since there are intrinsically different characteristics in utterances in different types of function segments, e.g., Monologue segments versus Discussion ones, we propose a new summarization framework where different summarizers are used for different segment types. For monologue segments, we adopt the integer linear programming-based summarization method; whereas for discussion segments, we use a graph-based method to incorporate speaker information. Performance of our proposed method is evaluated using the standard AMI meeting corpus. Results show a good improvement over previous... 

Linear segmentation of a meeting conversation is beneficial as a stand-alone system (to organize a meeting and make it easier to access) or as a preprocessing step for many other meeting related tasks. Such segmentation can be done according to two different criteria: topic in which a meeting is segmented according to the different items in its agenda, and function in which the segmentation is done according to the meeting's different events (like discussion, monologue). In this article we concentrate on the function segmentation task and propose new unsupervised methods to segment a meeting into functionally coherent parts. The first proposed method assigns a score to each possible boundary... 

In this paper we investigate the role of discourse analysis in extractive meeting summarization task. Specifically our proposed method comprises of two distinct steps. First we use a meeting segmentation algorithm in order to detect various functional parts of the input meeting. Afterwards, a two level scoring mechanism in a graph-based framework is used to score each dialogue act in order to extract the most valuable ones and include them in the extracted summary. We evaluate our proposed method on AMI and ICSI corpora and compare it with other state-of-the-art graph based algorithms according to various evaluation metrics. The experimental results show that our algorithm outperforms the... 

Here we have optimized shape and location of cooling passages of a C3X turbine blade using a multi-objective strategy. The objective functions is selected to be the maximum temperature gradient and the maximum temperature through the three dimensional blade. Shape of cooling channels is modeled using a new method based on the Bezier curves and using forty design variables. The optimized channel shapes are found to be smooth and without corners. To reduce the computational time, parallel processing and the reduced conjugate heat transfer methodology RCHT is used. Using RCHT, the heat transfer between channels and blade are coupled, while the experimental data is used for heat transfer... 

In this article we tackle the problem of multi-party conversation summarization. We investigate the role of discourse segmentation of a conversation on meeting summarization. First, an unsupervised function segmentation algorithm is proposed to segment the transcript into functionally coherent parts, such as Monologuei (which indicates a segment where speaker i is the dominant speaker, e.g., lecturing all the other participants) or Discussionx1x2,...,xn (which indicates a segment where speakers x 1 to xn involve in a discussion). Then the salience score for a sentence is computed by leveraging the score of the segment containing the sentence. Performance of our proposed segmentation and... 

This paper presents a solution in order to solve the problem of using HMM-based POS tagger in some languages where a word can be comprised of several tokens. Viterbi algorithm is modified in order to support segment of words within a model state. In the other word, the proposed system has a built-in tokenizer where indicates words boundaries as well as its corresponding tag sequence  

In this paper, we study the discriminative modeling of Spoken Language Understanding (SLU) using Conditional Random Fields (CRF) and Statistical Machine Translation (SMT) alignment models. Previous discriminative approaches to SLU have been dependent on n-gram features. Other previous works have used SMT alignment models to predict the output labels. We have used SMT alignment models to align the abstract labels and trained CRF to predict the labels. We show that the state transition features improve the performance. Furthermore, we have compared the proposed method with two baseline approaches; Hidden Vector States (HVS) and baseline-CRF. The results show that for the F-measure the proposed... 

This paper introduces Niusha, the first Persian speech-enabled IVR platform. This platform uses Persian recognizer and Persian text-to-speech synthesizer engines in order to interact with users. The platform is designed in a way that it can simply be customized in various domains and its components are adjustable with new words  

Over the years, detecting stable communities in a complex network has been a major challenge in network science. The global and local structures help to detect communities from different perspectives. However, previous methods based on them suffer from high complexity and fall into local optimum, respectively. The Four-Stage Algorithm (FSA) is proposed to reduce these issues and to allocate nodes to stable communities. Balancing global and local information, as well as accuracy and time complexity, while ensuring the allocation of nodes to stable communities, are the fundamental goals of this research. The Four-Stage Algorithm (FSA) is described and demonstrated using four real-world data... 

The key element of a spoken dialogue system is Spoken Language Understanding (SLU) part. HVS and EHVS are two most popular statistical methods employed to implement the SLU part which need lightly annotated data. Since annotation is a time consuming, we present a novel semi-supervised learning for EHVS to reduce the human labeling effort using two different statistical classifiers, SVM and KNN. Experiments are done on a Persian corpus, the University Information Kiosk corpus. The experimental results show improvements in performance of semi-supervised EHVS, trained by both labeled and unlabeled data, compared to EHVS trained by just initially labeled data. The performance of EHVS improves... 

In this paper, we study the problem of estimating the direction of arrival (DOA) using a sparsely sampled uniform linear array (ULA). Based on an initial incomplete ULA measurements, our strategy is to choose a sparse subset of array elements for measuring the next snapshot. Then, we use a Hankel-structured matrix completion to interpolate for the missing ULA measurements. Finally, the source DOAs are estimated using a subspace method such as Prony on the fully recovered ULA. We theoretically provide a sufficient bound for the number of required samples (array elements) for perfect recovery. The numerical comparisons of the proposed method with existing techniques such as atomic-norm...