The use of Voice Source Features for Sung Speech Recognition.
Gerardo Roa DabikeJon BarkerPublished in: ICASSP (2021)
Keyphrases
- speech recognition
- speech recognition systems
- speech synthesis
- mel frequency cepstral coefficients
- hidden markov models
- speech recognition errors
- pattern recognition
- language model
- speech recognizer
- speech recognition technology
- keyword spotting
- feature set
- speech signal
- speech understanding
- speaker identification
- noisy environments
- speech processing
- feature extraction
- automatic speech recognition
- low level
- feature space
- cepstral coefficients
- speech retrieval
- speech recognizers
- speaker recognition
- voice activity detection
- computer vision
- image processing