English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a novel method that trains pass-phrase specificdeep neural network (PP-DNN) based auto-encoders for creating augmented datafor text-dependent speaker verification (TD-SV). Each PP-DNN auto-encoder istrained using the utterances of a particular pass-phrase available in thetarget enrollment set with two methods: (i) transfer learning and (ii) trainingfrom scratch. Next, feature vectors of a given utterance are fed to the PP-DNNsand the output from each PP-DNN at frame-level is considered one new set ofgenerated data. The generated data from each PP-DNN is then used for building aTD-SV system in contrast to the conventional method that considers only theevaluation data available. The proposed approach can be considered as thetransformation of data to the pass-phrase specific space using a non-lineartransformation learned by each PP-DNN. The method develops several TD-SVsystems with the number equal to the number of PP-DNNs separately trained foreach pass-phrases for the evaluation. Finally, the scores of the differentTD-SV systems are fused for decision making. Experiments are conducted on theRedDots challenge 2016 database for TD-SV using short utterances. Results showthat the proposed method improves the performance for both conventionalcepstral feature and deep bottleneck feature using both Gaussian mixture model- universal background model (GMM-UBM) and i-vector framework.

Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification