Loading [MathJax]/extensions/MathZoom.js
But ASR system for BABEL Surprise evaluation 2014 | IEEE Conference Publication | IEEE Xplore

But ASR system for BABEL Surprise evaluation 2014


Abstract:

The paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil). While being largely based on our previous work, tw...Show More

Abstract:

The paper describes Brno University of Technology (BUT) ASR system for 2014 BABEL Surprise language evaluation (Tamil). While being largely based on our previous work, two original contributions were brought: (1) speaker-adapted bottle-neck neural network (BN) features were investigated as an input to DNN recognizer and semi-supervised training was found effective. (2) Adding of noise to training data outperformed a classical de-noising technique while dealing with noisy test data was found beneficial, and the performance of this approach was verified on a relatively clean training/test data setup from a different language. All results are reported on BABEL 2014 Tamil data.
Date of Conference: 07-10 December 2014
Date Added to IEEE Xplore: 02 April 2015
Electronic ISBN:978-1-4799-7129-9
Conference Location: South Lake Tahoe, NV, USA

References

References is not available for this document.