On the Usefulness of Statistical Normalisation of Bottleneck Features for Speech Recognition.
Erfan LoweimiPeter BellSteve RenalsPublished in: ICASSP (2019)
Keyphrases
- speech recognition
- speech recognition systems
- speech signal
- pattern recognition
- cepstral coefficients
- speech synthesis
- hidden markov models
- language model
- speech processing
- noisy environments
- automatic speech recognition
- feature extraction
- handwriting recognition
- feature set
- speech recognizer
- speech understanding
- extracting features
- structural features
- feature vectors
- feature space
- isolated word
- audio visual speech recognition
- digital video library