Automatic estimation of the first two subglottal resonances in children's speech with application to speaker normalization in limited-data conditions.
Harish ArsikereGary K. F. LeungSteven M. LulichAbeer AlwanPublished in: INTERSPEECH (2012)
Keyphrases
- data sets
- data collection
- raw data
- spatial data
- data sources
- database
- data processing
- data quality
- original data
- speech recognition
- statistical analysis
- preprocessing
- high quality
- training data
- databases
- data mining techniques
- data points
- sufficient conditions
- computer systems
- data analysis
- data structure
- data mining
- audio visual
- experimental conditions