Evaluating two versions of the momel pitch modelling algorithm on a corpus of read speech in Korean.
Daniel HirstHyongsil ChoSunhee KimHyunji YuPublished in: INTERSPEECH (2007)
Keyphrases
- preprocessing
- learning algorithm
- k means
- detection algorithm
- matching algorithm
- significant improvement
- search space
- cost function
- dynamic programming
- computational complexity
- improved algorithm
- times faster
- neural network
- particle swarm optimization
- expectation maximization
- speech recognition
- ant colony optimization
- speech signal
- optimization algorithm
- theoretical analysis
- high accuracy
- worst case
- denoising
- probabilistic model
- similarity measure