The Telefonica Research Spoken Web Search System for MediaEval 2013
نویسندگان
چکیده
In this paper we describe the system proposed by Telefonica research for the Spoken Web Search (SWS) task [3] within the Mediaeval 2013 evaluation. This is the third year we participate in the evaluation and this time we have submitted a system based on the recently proposed Information Retrieval-based Dynamic Time Warping (IR-DTW) Algorithm. This algorithm performs a pattern matching search at frame level similar to the DTW algorithm, but with advantages in memory usage and the possibility to with preindex the search corpora and use fast retrieval techniques. Results obtained this year have been poorer than expected, most probably due to the use of a global voice activity detector that was not adequate to the varying nature of the different acoustic conditions in this year’s search corpora.
منابع مشابه
LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based Approach
In this paper, we describe the LIA system proposed for the MediaEval 2013 Spoken Web Search task. This multilanguage task involves searching for an audio content query, in a database, with no training resources available. The participants must then find locations of each given query term within a large database of untranscribed audio files. For this task, we propose to build a language-independ...
متن کاملELiRF at MediaEval 2013: Spoken Web Search Task
In this paper, we present the systems that the Natural Language Engineering and Pattern Recognition group (ELiRF) has submitted to the MediaEval 2013 Spoken Web Search task. All of them are based on a Subsequence Dynamic Time Warping algorithm and are zero-resources systems.
متن کاملIrisa MediaEval 2011 Spoken Web Search System
These working notes describe the main aspects of IRISA submission for the Spoken Web Search at the MediaEval 2011 campaign. We test a language-independent audio-only system based on a combination of template matching techniques. A brief overview of the main components of the architecture is followed by reporting on the evaluation on the development and test data provided by the organizers.
متن کاملThe L2F Spoken Web Search system for Mediaeval 2012
This document presents a brief description of INESC-ID’s Spoken Language Systems Laboratory (LF) Spoken Web Search system submitted to the Mediaeval 2012 evaluation campaign. The LF system consists of the fusion of four individual sub-systems based on hybrid approaches for speech recognition exploiting four different language-dependent phonetic classifiers. The achieved results confirm the prop...
متن کاملThe JHU-HLTCOE Spoken Web Search System for MediaEval 2012
We present an overview for a truly zero resource query-byexample search system designed for the 2012 MediaEval Spoken Web Search task. Our system is based on the recently proposed randomized acoustic indexing and logarithmictime search (RAILS) framework. The input is merely the raw acoustic observations for the query and search collection, requiring no trained models whatsoever, not even unsupe...
متن کامل