Combining Non-Pathological Data of Different Language Varieties to Improve DNN-HMM Performance on Pathological Speech.
Emre YilmazMario GanzeboomCatia CucchiariniHelmer StrikPublished in: INTERSPEECH (2016)
Keyphrases
- data sets
- data collection
- data analysis
- data structure
- original data
- database
- databases
- sensor data
- data sources
- image data
- data processing
- training data
- experimental data
- missing data
- computer systems
- small number
- knowledge discovery
- data points
- hidden markov models
- database systems
- natural language processing
- input data
- machine learning
- high quality