%Aigaion2 BibTeX export from Idiap Publications
%Monday 29 April 2024 08:40:24 AM

@TECHREPORT{Ram_Idiap-RR-06-2016,
         author = {Ram, Dhananjay and Asaei, Afsaneh and Bourlard, Herv{\'{e}}},
       keywords = {Deep neural network posterior probabilities , Dictionary learning, sparse representation, Subspace detection },
       projects = {Idiap},
          month = {4},
          title = {Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection},
           type = {Idiap-RR},
         number = {Idiap-RR-06-2016},
           year = {2016},
    institution = {Idiap},
       crossref = {Ram_Idiap-RR-01-2016},
       abstract = {We cast the query by example spoken term detection (QbE-STD) problem as subspace detection where query and background subspaces are modeled as union of low-dimensional subspaces. The speech exemplars used for subspace modeling are class-conditional posterior probabilities estimated using deep neural network (DNN). The query and background training exemplars are exploited to model the underlying low-dimensional subspaces through dictionary learning for sparse representation. Given the dictionaries characterizing the query and background subspaces, QbE-STD is performed based on the ratio of the two corresponding sparse representation reconstruction errors. The proposed subspace detection method can be formulated as the generalized likelihood ratio test for composite hypothesis testing. The experimental evaluation demonstrate that the proposed method is able to detect the query given a single example and performs significantly better than a highly competitive QbE-STD baseline system based on template matching.},
            pdf = {https://publications.idiap.ch/attachments/reports/2016/Ram_Idiap-RR-06-2016.pdf}
}



crossreferenced publications: 
@TECHREPORT{Ram_Idiap-RR-01-2016,
         author = {Ram, Dhananjay and Asaei, Afsaneh and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          month = {1},
          title = {Sparse Subspace Modeling for Query by Example Spoken Term Detection},
           type = {Idiap-RR},
         number = {Idiap-RR-01-2016},
           year = {2016},
    institution = {Idiap},
       abstract = {We cast the problem of query by example spoken term detection (QbE-STD) as subspace detection where query and background are modeled as a union of low-dimensional subspaces. The speech exemplars used for subspace modeling consist of class-conditional posterior probabilities obtained from deep neural network (DNN). The query and background training exemplars are exploited to model the underlying low-dimensional subspaces through dictionary learning and sparse coding. Given the dictionaries characterizing the query and background speech, QbE-STD amounts to subspace detection via sparse representation and the reconstruction error is used for binary classification. Furthermore, we rigorously investigate the relationship between the proposed method and the generalized likelihood ratio test. The experimental evaluation demonstrate that the proposed method is able to detect the query given a single exemplar and performs significantly better than one of the best QbE-STD baseline systems based on template matching.},
            pdf = {https://publications.idiap.ch/attachments/reports/2016/Ram_Idiap-RR-01-2016.pdf}
}