Unsupervised Bottleneck features for low-resource query-by-example spoken term detection

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 performs comparably with the cross-lingual bottleneck features (BNFs) extracted from a DNN trained using 171 hours of transcribed telephone speech in another language (Mandarin Chinese). 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. We also study the performance of the framework with different input features and different lengths of temporal context.