Abstract | ||
---|---|---|
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 three-state phoneme posteriors as input features. Our main contribution was m-norm normalization of particular subsystems together with the fusion based on binary logistic regression. The results, including per-language analysis, are provided on MediaEval 2013 dataset. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICASSP.2014.6855128 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
acoustic signal processing,natural language processing,query processing,regression analysis,speech processing,MediaEval 2013 Spoken Web Search task evaluations,MediaEval 2013 dataset,SWS 2013,acoustic keyword spotting,binary logistic regression,dynamic time warping,m-norm normalization,per-language analysis,query-by-example systems,three-state phoneme posteriors,TWV,acoustic keyword spotting,dynamic time warping,fusion,m-norm,query-by-example spoken term detection,z-norm | Speech processing,Normalization (statistics),Dynamic time warping,Computer science,Regression analysis,Keyword spotting,Artificial intelligence,Natural language processing,Artificial neural network,Pattern recognition,Speech recognition,Query by Example,Calibration | Conference |
ISSN | Citations | PageRank |
1520-6149 | 13 | 0.99 |
References | Authors | |
8 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Igor Szöke | 1 | 310 | 22.64 |
Lukás Burget | 2 | 13 | 0.99 |
Frantisek Grézl | 3 | 389 | 38.12 |
Jan Cernocký | 4 | 1273 | 135.94 |
Lucas Ondel | 5 | 35 | 7.16 |