Voice Quality and Pitch Features in Transformer-Based Speech Recognition.
Guillermo CámbaraJordi LuqueMireia FarrúsPublished in: CoRR (2021)
Keyphrases
- speech recognition
- speech recognition systems
- speech synthesis
- pattern recognition
- hidden markov models
- speech recognition errors
- mel frequency cepstral coefficients
- language model
- speech signal
- speech processing
- speech understanding
- noisy environments
- automatic speech recognition
- speaker identification
- cepstral coefficients
- voice activity detection
- low level
- feature vectors
- speech recognition technology
- feature space
- speaker diarization
- speech recognizer
- feature set
- classification accuracy
- speaker independent
- speech retrieval