Power-Law Nonlinearity with Maximally Uniform Distribution Criterion for Improved Neural Network Training in Automatic Speech Recognition.
Chanwoo KimMehul KumarKwangyoun KimDhananjaya GowdaPublished in: ASRU (2019)
Keyphrases
- uniform distribution
- power law
- automatic speech recognition
- neural network training
- speech recognition
- pac learning
- boolean functions
- speech signal
- hidden markov models
- neural network
- conversational speech
- small world
- speech retrieval
- broadcast news
- training algorithm
- membership queries
- noisy environments
- monotone boolean functions
- information extraction
- optimization method
- data sets
- speech sounds