HMM adaptation using linear spline interpolation with integrated spline parameter training for robust speech recognition.
Michael L. SeltzerAlex AceroPublished in: INTERSPEECH (2010)
Keyphrases
- speech recognition
- spline interpolation
- hidden markov models
- speaker adaptation
- wall street journal corpus
- noisy environments
- cubic spline interpolation
- speech signal
- isolated word
- automatic speech recognition
- acoustic models
- boundary conditions
- pattern recognition
- language model
- speech synthesis
- speech recognizer
- speech processing
- keyword spotting
- speaker identification
- speech recognition technology
- speaker independent
- speech retrieval
- speaker dependent
- machine learning
- discriminative training
- training process
- speech recognition systems
- signal processing
- computer vision
- neural network
- n gram
- sufficient conditions
- multiresolution
- training set
- speech recognizers