This paper summarizes our work for MediaEval 2013 Spoken Web Search task evaluations. The task was Query-by-Example (search of spoken queries within spoken data). We submitted a system composed of 26 subsystems, of which 13 are based on Acoustic Keyword Spotting and 13 on Dynamic Time Warping. All of them use threestate phoneme posteriors as input features. Our main contribution was m-norm norm...

We present a study we conducted to build a repository storing associations between simple dependency treelets in a source language and their corresponding phrases in a target language. To assess the impact of this resource in EBMT, we used the repository to compute coverage statistics on a test bitext and on a nbest list of translation candidates produced by a standard phrase-based decoder.

Because syntactic structures and spans of multiword expressions (MWEs) are independently annotated in many English syntactic corpora, they are generally inconsistent with respect to one another, which is harmful to the implementation of an aggregate system. In this work, we construct a corpus that ensures consistency between dependency structures and MWEs, including named entities. Further, we ...

A hierarchical system for audio classi cation and retrieval based on audio content analysis is presented in this paper. The system consists of three stages. The rst stage is called the coarse-level audio classi cation and segmentation, where audio recordings are classi ed and segmented into speech, music, several types of environmental sounds, and silence, based on morphological and statistical...

Due to small available English-Bangla parallel corpus, Example-Based Machine Translation (EBMT) system has high probability of handling unknown words. To improve translation quality for Bangla language, we propose a novel approach for EBMT using WordNet and International-Phonetic-Alphabet(IPA)-based transliteration. Proposed system first tries to find semantically related English words from Wor...

The issue of flexibility of multiword expressions (MWEs) is crucial towards their identification and extraction in running text, as well as their better understanding from a linguistic perspective. If we project a large MWE lexicon onto a corpus, projecting fixed forms suffers from low recall, while an unconstrained flexible search for lemmas yields a loss in precision. In this talk, I will des...

The Kutch Earthquake of January 26, 2001 in Gujarat, India, caused the destruction of a large number of modern 4 to 10-storied buildings. After this earthquake, doubts arose about our professional practices, building by-laws, construction materials, building codes and education for civil engineers and architects. It led to large number of short-term courses and workshops, revision of the seismi...

In this paper we examine an alternative interface for phonetic search, namely query-by-example, that avoids OOV issues associated with both standard word-based and phonetic search methods. We develop three methods that compare query lattices derived from example audio against a standard ngrambased phonetic index and we analyze factors affecting the performance of these systems. We show that the...

This working paper provides the basic information about experiments conducted on audio documents within the MediaEval 2012 spoken web search evaluation project. The main purpose of these experiments was to build a robust and language independent system for spoken term detection. Therefore we have proposed query-by-example searching system based on the minimum-cost alignment of DTW algorithm and...

Multimedia, as it stands now is perhaps the most diverse and rich culture around the globe. One of the major needs of Multimedia is to have a single system that enables people to efficiently search through their multimedia catalogues. Many Domain Specific Systems and architectures have been proposed but up till now no generic and complete architecture is proposed. In this paper, we have suggest...