From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition.
Duc LeXiaohui ZhangWeiyi ZhengChristian FügenGeoffrey ZweigMichael L. SeltzerPublished in: ASRU (2019)
Keyphrases
- speech recognition
- context dependent
- hidden markov models
- speech synthesis
- language model
- speech recognizer
- automatic speech recognition
- speech recognition technology
- natural language
- pattern recognition
- speech understanding
- low level
- speech recognition systems
- noisy environments
- speech processing
- cepstral coefficients
- keyword spotting
- high level
- speaker identification
- speech signal
- speaker recognition
- speech recognizers
- isolated word
- bayesian networks
- machine learning