Ensembles of Multi-Scale VGG Acoustic Models.
Michael HeckMasayuki SuzukiTakashi FukudaGakuto KurataSatoshi NakamuraPublished in: INTERSPEECH (2017)
Keyphrases
- multiscale
- acoustic models
- speech recognition
- hidden markov models
- speech recognizer
- automatic speech recognition
- decision trees
- image processing
- broadcast news
- edge detection
- image representation
- image segmentation
- discriminative training
- language model
- speaker independent
- pattern recognition
- training data
- spoken language
- multimedia
- data sets