Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech.
Emre YilmazVikramjit MitraGanesh SivaramanHoracio FrancoPublished in: Comput. Speech Lang. (2019)
Keyphrases
- speech recognition
- speaker independent
- automatic speech recognition
- speech recognition systems
- speech signal
- speaker dependent
- speech recognizer
- emotion classification
- hidden markov models
- speech synthesis
- speaker identification
- speaker adaptation
- noisy environments
- pattern recognition
- language model
- feature vectors
- vocal tract
- feature extraction
- neural network
- acoustic models
- acoustic features
- low level
- extracting features
- lexical features
- mel frequency cepstral coefficients
- digit recognition
- non stationary
- feature space
- multimedia
- information retrieval