Text-Independent/Text-Prompted Speaker Recognition by Combining Speaker-Specific GMM with Speaker Adapted Syllable-Based HMM.
Seiichi NakagawaWei ZhangMitsuo TakahashiPublished in: IEICE Trans. Inf. Syst. (2006)
Keyphrases
- speaker recognition
- gaussian mixture model
- speaker verification
- speaker identification
- vector quantization
- speech recognition
- probabilistic neural network
- speech signal
- prosodic features
- keywords
- hidden markov models
- information retrieval
- text mining
- mixture model
- feature space
- mel frequency cepstral coefficients
- neural network
- noisy environments
- gaussian process regression
- text data