Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition.
Vishwas M. ShettyRini A. SharonBasil AbrahamTejaswi SeeramAnusha PrakashNithya RaviSrinivasan UmeshPublished in: INTERSPEECH (2018)
Keyphrases
- speech recognition
- speech recognition systems
- hidden markov models
- speech synthesis
- language model
- speech processing
- speech signal
- speech recognizer
- automatic speech recognition
- cepstral coefficients
- speech understanding
- pattern recognition
- noisy environments
- handwriting recognition
- speech recognition technology
- speaker identification
- mel frequency cepstral coefficients
- speaker independent
- speech recognition errors
- neural network
- isolated word
- low level
- information retrieval
- speaker diarization
- feature set
- natural language processing
- feature extraction
- image processing
- feature selection