Large vocabulary Korean continuous speech recognition using a one-pass algorithm.
Ha-Jin YuHoon KimJoon-Mo HongMin-Seong KimJong-Seok LeePublished in: INTERSPEECH (2000)
Keyphrases
- np hard
- computational cost
- preprocessing
- clustering method
- dynamic programming
- experimental evaluation
- high accuracy
- improved algorithm
- simulated annealing
- times faster
- search space
- significant improvement
- cost function
- detection algorithm
- computationally efficient
- estimation algorithm
- worst case
- expectation maximization
- theoretical analysis
- recognition algorithm
- single pass
- particle swarm optimization
- input data
- data sets
- k means
- objective function
- learning algorithm
- probabilistic model
- segmentation algorithm
- hidden markov models
- artificial neural networks
- computational complexity
- selection algorithm
- optimal solution
- hardware implementation