Improving Speech Recognition with Drop-in Replacements for f-Bank Features.
Sean RobertsonGerald PennYingxue WangPublished in: SLSP (2019)
Keyphrases
- speech recognition
- speech recognition systems
- cepstral coefficients
- hidden markov models
- language model
- speech processing
- pattern recognition
- automatic speech recognition
- speech synthesis
- feature space
- noisy environments
- speech signal
- speech recognizer
- speaker independent
- speech recognition technology
- speech recognizers
- feature extraction
- speaker identification
- feature vectors
- speech understanding
- extracted features
- feature set
- classification accuracy
- speech recognition errors
- computer vision
- audio visual speech recognition