From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition.
Duc LeXiaohui ZhangWeiyi ZhengChristian FügenGeoffrey ZweigMichael L. SeltzerPublished in: CoRR (2019)
Keyphrases
- speech recognition
- context dependent
- hidden markov models
- speech recognizer
- language model
- automatic speech recognition
- speech recognition technology
- pattern recognition
- speech signal
- speech synthesis
- speech understanding
- low level
- noisy environments
- speech processing
- speech recognition systems
- speaker dependent
- keyword spotting
- speaker independent
- isolated word
- speaker identification
- natural language
- computer vision
- information retrieval
- natural language processing
- cepstral coefficients
- speech retrieval
- neural network