Combining Articulatory Features with End-to-End Learning in Speech Recognition.
Leyuan QuCornelius WeberEgor LakomkinJohannes TwiefelStefan WermterPublished in: ICANN (3) (2018)
Keyphrases
- speech recognition
- end to end
- speech recognition systems
- automatic speech recognition
- speech processing
- speech signal
- computer vision
- hidden markov models
- pattern recognition
- feature extraction
- speech synthesis
- cepstral coefficients
- language model
- neural network
- speech recognition technology
- feature set
- word recognition
- congestion control
- speaker identification
- image processing
- isolated word