Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech.
Heidi ChristensenM. B. AniolPeter BellPhil D. GreenThomas HainSimon KingPawel SwietojanskiPublished in: INTERSPEECH (2013)
Keyphrases
- automatic recognition
- data collection
- data sets
- domain specific
- synthetic data
- data processing
- domain experts
- data analysis
- end users
- speech recognition
- missing data
- high dimensional data
- statistical analysis
- input data
- data sources
- high quality
- learning algorithm
- raw data
- databases
- data structure
- training data
- image data
- experimental data
- original data