Automatic Annotation of Speech Corpora Using Complementary GMM and DNN Acoustic Models.
Alexandru-Lucian GeorgescuHoria CucuPublished in: TSP (2018)
Keyphrases
- automatic annotation
- acoustic models
- speech recognition
- speaker identification
- broadcast news
- speaker independent
- automatic speech recognition
- speech recognizer
- gaussian mixture model
- hidden markov models
- training process
- speaker recognition
- speech signal
- content based retrieval
- semantic annotation
- image annotation
- visual information
- noisy environments
- natural language processing
- spoken language
- low level features
- image database
- mixture model
- video retrieval
- pattern recognition
- mel frequency cepstral coefficients
- image retrieval
- text data
- em algorithm
- language model
- visual features
- generative model
- video search
- multi modal
- image understanding
- feature vectors