Unsupervised Bottleneck Features for Low-Resource Query-by-Example Spoken Term Detection

  title={Unsupervised Bottleneck Features for Low-Resource Query-by-Example Spoken Term Detection},
  author={Hongjie Chen and Cheung-Chi Leung and Lei Xie and Bin Ma and Haizhou Li},
We propose a framework which ports Dirichlet Gaussian mixture model (DPGMM) based labels to deep neural network (DNN). The DNN trained using the unsupervised labels is used to extract a low-dimensional unsupervised speech representation, named as unsupervised bottleneck features (uBNFs), which capture considerable information for sound cluster discrimination. We investigate the performance of uBNF in queryby-example spoken term detection (QbE-STD) on the TIMIT English speech corpus. Our uBNF… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • With the score fusion of uBNFs and cross-lingual BNFs, we gain about 10% relative improvement in terms of mean average precision (MAP) comparing with the cross-lingual BNFs.


Publications citing this paper.
Showing 1-10 of 18 extracted citations

Acceleration for query-by-example using posteriorgram of deep neural network

2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) • 2017
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 28 references

Resource configurable spoken query detection using Deep Boltzmann Machines

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 9 Excerpts
Highly Influenced

The Kaldi Speech Recognition Toolkit

View 3 Excerpts
Highly Influenced

Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams

2009 IEEE Workshop on Automatic Speech Recognition & Understanding • 2009
View 6 Excerpts
Highly Influenced

Unsupervised Pattern Discovery in Speech

IEEE Transactions on Audio, Speech, and Language Processing • 2008
View 5 Excerpts
Highly Influenced

Exploring multi-language resources for unsupervised spoken term discovery

2015 International Conference on Speech Technology and Human-Computer Dialogue (SpeD) • 2015
View 1 Excerpt

Nonparametric bayesian approaches for acoustic modeling

A. H. Harati Nejad Torbati
Ph.D. dissertation, TEMPLE UNIVERSI- TY, 2015. • 2015
View 1 Excerpt

Unsupervised neural network based feature extraction using weak top-down constraints

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…