End-to-end speech recognition from raw speech: Multi time-frequency resolution CNN architecture for efficient representation learning.
Dhanya EledathP. InbarajanAnurag BiradarSathwick MahadevaV. RamasubramanianPublished in: EUSIPCO (2021)
Keyphrases
- speech recognition
- end to end
- speech signal
- speech processing
- speech synthesis
- language model
- hidden markov models
- speaker identification
- automatic speech recognition
- speech recognizer
- speech recognition technology
- noisy environments
- speaker recognition
- speech recognition systems
- speaker independent
- speech recognition errors
- congestion control
- pattern recognition
- speech recognizers
- keyword spotting
- word error rate
- probabilistic model
- multiresolution