Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection.
Cheng-Tao ChungCheng-Yu TsaiChia-Hsiang LiuLin-Shan LeePublished in: CoRR (2017)
Keyphrases
- deep learning
- unsupervised feature learning
- unsupervised learning
- spoken term detection
- deep architectures
- weakly supervised
- image features
- speech recognition
- hidden markov models
- low level
- computer vision
- feature set
- hand crafted
- automatic speech recognition
- semi supervised
- information extraction
- keywords
- multiscale
- feature selection