ACL RD-TEC 1.0 Summarization of H89-2062
Paper Title:
SEGMENT-BASED ACOUSTIC MODELS WITH MULTI-LEVEL SEARCH ALGORITHMS FOR CONTINUOUS SPEECH RECOGNITION
SEGMENT-BASED ACOUSTIC MODELS WITH MULTI-LEVEL SEARCH ALGORITHMS FOR CONTINUOUS SPEECH RECOGNITION
Authors: Mari Ostendorf and J. Robin Rohlicek
Primarily assigned technology terms:
- acoustic modelling
- algorithm
- classification
- classification system
- context modelling
- continuous speech recognition
- database
- iterative search
- iterative search algorithm
- modelling
- parameter estimation
- parameter reduction
- phomeme recognition
- phoneme classification
- phoneme recognition
- recognition
- recognition systems
- search
- search algorithm
- speaker-independent phoneme classification
- speaker-independent recognition
- speech recognition
Other assigned terms:
- acoustic models
- continuous speech
- correlation
- duration
- estimation
- feature
- feature vectors
- formalism
- phoneme
- stochastic segment model
- timit database
- training
- training data
