Phonological Posterior Hashing for Query by Example Spoken Term Detection

Afsaneh Asaei, Dhananjay Ram, Hervé Bourlard


State of the art query by example spoken term detection (QbE-STD) systems in zero-resource conditions 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 a large audio 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 solution based on DTW. The system has the potential to enable massively large scale spoken query detection.


 DOI: 10.21437/Interspeech.2018-1973

Cite as: Asaei, A., Ram, D., Bourlard, H. (2018) Phonological Posterior Hashing for Query by Example Spoken Term Detection. Proc. Interspeech 2018, 2067-2071, DOI: 10.21437/Interspeech.2018-1973.


@inproceedings{Asaei2018,
  author={Afsaneh Asaei and Dhananjay Ram and Hervé Bourlard},
  title={Phonological Posterior Hashing for Query by Example Spoken Term Detection},
  year=2018,
  booktitle={Proc. Interspeech 2018},
  pages={2067--2071},
  doi={10.21437/Interspeech.2018-1973},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1973}
}