Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation.
Dan BerrebbiJiatong ShiBrian YanOsbel López-FranciscoJonathan D. AmithShinji WatanabePublished in: CoRR (2022)
Keyphrases
- speech recognition
- cepstral coefficients
- speech recognition systems
- speech synthesis
- language model
- hidden markov models
- pattern recognition
- speech processing
- spectral features
- speech signal
- automatic speech recognition
- neural network
- low level
- feature set
- speaker independent
- spectral analysis
- speaker identification
- feature space
- speech recognition technology
- speech understanding
- speech recognizers
- keyword spotting
- speech recognizer
- noisy environments
- feature extraction
- speaker recognition
- speaker adaptation
- speech recognition errors
- computer vision
- machine learning