• There is no summary for this article.

Summary

• We present two methods to select the most relevant features among a large set of acoustic features, for the purpose of estimating the relevance of each feature using the costs of the best alignment path (obtained when performing DTW) and their neighbouring region.
• To prove the validity of these methods, experiments were carried out in four different search on speech scenarios that were used in international benchmarks, namely Albayzin 2014 search on speech evaluation, MediaEval spoken web search SWS 2013, and MediaEval query-by-example search on speech QUESST2014 and QUESST2015.
• A comparison between the proposed methods and other representations such as MFCCs, phonetic posteriorgrams and dimensionality reduction based on principal component analysis, showed that the zero-resource approaches presented in this paper are promising, as they outperformed more extended approaches in all the experimental scenarios.

Summary

• For this paper a computer program has been written to simulate the way bees search for new hives and investigate whenever it is an optimal method to search for cave entrances on Mars.
• The simulation results show that 50 swarm robots can cover an area of over 300 meters square completely in 5 sols while they are searching for cave entrances and returning results to the Lander which is a major performance improvement on any previous mission.
• Furthermore areas of interests found by the explorers are sorted in order of importance automatically and without the need of computational analysis, hence larger quantities of data were collected from the more important areas.

• There is no summary for this article.

Summary

• Recent work has shown that comparing speech segments by representing them as fixed-dimensional vectors --- acoustic word embeddings --- and measuring their vector distance (e.g., cosine distance) can discriminate between words more accurately than DTW-based approaches.
• We consider an approach to query-by-example search that embeds both the query and database segments according to a neural model, followed by nearest-neighbor search to find the matching segments.
• We find that our embeddings, based on recurrent neural networks trained to optimize word discrimination, achieve substantial improvements in performance and run-time efficiency over the previous approaches.

• There is no summary for this article.

• There is no summary for this article.

• There is no summary for this article.

Summary

• The qualitative shape and colour similarity theories are applied to the problem of matching icon images.
• The suitability of this approach as a foundation for a practical query by example engine for icons is shown by an experimental evaluation.
• The use of a more cognitive approach opens the possibility of creating systems that can be tailored to particular user requirements involving complex rules that cannot be handled by current systems.

• There is no summary for this article.

• There is no summary for this article.

• There is no summary for this article.

• There is no summary for this article.

Summary

• This paper presents a neighborhood graph index approach for query-by-example search using dynamic time warping (DTW) on Gaussian mixture model (GMM) posteriorgram sequences.
• By applying a newly introduced combination of greedy-search (GS) and breadth-first search (BFS) algorithms to the selected k-DR graph index, the proposed method efficiently achieves query-by-example STD.
• Experimental results on the MIT lecture corpus demonstrate that the proposed method works much faster than a state-of-art method by more than one order magnitude, keeping almost the same precision.

• There is no summary for this article.

• There is no summary for this article.

Summary

• We present the systems that the Natural Language Engineering and Pattern Recognition group (ELiRF) has submitted to the MediaEval 2014 Query by Example Search on Speech task.
• All of them are based on a Subsequence Dynamic Time Warping algorithm and do not use any other information from outside the task (zero-resources systems ).

• There is no summary for this article.

• There is no summary for this article.

• There is no summary for this article.