But ASR system for BABEL Surprise evaluation 2014
Autor: | Frantisek Grezl, Karel Vesely, Mirko Hannemann, Igor Szöke, Jan Cernocky, Lukas Burget, Martin Karafiat |
---|---|
Rok vydání: | 2014 |
Předmět: |
Training set
Artificial neural network Computer science business.industry media_common.quotation_subject Speech recognition computer.software_genre language.human_language Surprise Tamil language Deep neural networks Noise (video) Artificial intelligence business computer Natural language processing media_common Test data |
Zdroj: | SLT |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |