Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data.
Heidi ChristensenI. CasanuevaStuart P. CunninghamPhil D. GreenThomas HainPublished in: SLT (2014)
Keyphrases
- sparse data
- automatic selection
- speech recognition
- speaker independent
- speech recognition systems
- speech sounds
- speaker dependent
- noisy speech
- recognition engine
- high dimensional
- automatic speech recognition
- speech signal
- hidden markov models
- vowel phonemes
- speech synthesis
- speech recognizer
- speaker identification
- formant frequencies
- noisy environments
- object recognition
- language model
- pattern recognition
- speaker adaptation
- feature extraction
- dimensionality reduction
- multi dimensional
- unsupervised learning
- multi category
- visual speech
- vocal tract
- text to speech
- random projections