Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation.
Dan BerrebbiJiatong ShiBrian YanOsbel López-FranciscoJonathan D. AmithShinji WatanabePublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- cepstral coefficients
- speech recognition systems
- speech recognizer
- speech synthesis
- language model
- pattern recognition
- hidden markov models
- speech signal
- feature vectors
- feature set
- noisy environments
- speech understanding
- speaker identification
- spectral features
- speech processing
- speech recognition technology
- speech recognition errors
- feature extraction
- structural features
- feature space
- spectral analysis
- speaker independent
- speaker adaptation
- natural language
- image processing