%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 08:25:07 AM

@INPROCEEDINGS{Asaei_PHONOLOGICALPOSTERIORHASHINGFORQUERYBYEXAMPLESPOKENTERMDETECTION_2018,
         author = {Asaei, Afsaneh and Ram, Dhananjay and Bourlard, Herv{\'{e}}},
       projects = {Idiap, PHASER-QUAD},
          title = {Phonological Posterior Hashing for Query by Example Spoken Term Detection},
      booktitle = {Proceedings of Interspeech},
           year = {2018},
       crossref = {Asaei_Idiap-RR-31-2016},
            pdf = {https://publications.idiap.ch/attachments/papers/2018/Asaei_PHONOLOGICALPOSTERIORHASHINGFORQUERYBYEXAMPLESPOKENTERMDETECTION_2018.pdf}
}



crossreferenced publications: 
@TECHREPORT{Asaei_Idiap-RR-31-2016,
         author = {Asaei, Afsaneh and Ram, Dhananjay and Bourlard, Herv{\'{e}}},
       keywords = {Posterior hashing, Posterior probability structures, Pronunciation dewarping, Structural similarity measure},
       projects = {Idiap, PHASER 200021-153507, PHASER-QUAD},
          month = {12},
          title = {Redundant Hash Addressing for Large-Scale Query by Example Spoken Query Detection},
           type = {Idiap-RR},
         number = {Idiap-RR-31-2016},
           year = {2016},
    institution = {Idiap},
       abstract = {State of the art query by example spoken term detection (QbE-STD) systems rely on representation of speech in terms of sequences of class-conditional posterior probabilities estimated by deep neural network (DNN). The posteriors are often used for pattern matching or dynamic time warping (DTW). 
Exploiting posterior probabilities as speech representation propounds diverse advantages in a classification system. One key property of the posterior representations is that they admit a highly effective hashing strategy that enables indexing the large archive in divisions for reducing the search complexity. Moreover, posterior indexing leads to a compressed representation and enables pronunciation dewarping and partial detection with no need for DTW. We exploit these characteristics of the posterior space in the context of redundant hash addressing for query-by-example spoken term detection (QbE-STD). We evaluate the QbE-STD system on AMI corpus and demonstrate that tremendous speedup and superior accuracy is achieved compared to the state-of-the-art pattern matching and DTW solutions. The system has great potential to enable massively large scale query detection.},
            pdf = {https://publications.idiap.ch/attachments/reports/2016/Asaei_Idiap-RR-31-2016.pdf}
}