Combination of hidden Markov models with dynamic time warping for speech recognition.
Scott AxelrodBenoît MaisonPublished in: ICASSP (1) (2004)
Keyphrases
- speech recognition
- hidden markov models
- dynamic time warping
- speech processing
- distance measure
- automatic speech recognition
- speech signal
- euclidean distance
- similarity measure
- speech synthesis
- speech recognizer
- keyword spotting
- speaker identification
- speech recognition systems
- edit distance
- sequential data
- handwriting recognition
- similarity search
- noisy environments
- pattern recognition
- neural network
- discriminative training
- speaker independent
- acoustic models
- high dimensional
- feature extraction
- computer vision
- machine learning
- data mining