On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models.
Xiaohui ZhangVimal ManoharDavid ZhangFrank ZhangYangyang ShiNayan SinghalJulian ChanFuchun PengYatharth SarafMike SeltzerPublished in: ASRU (2021)
Keyphrases
- automatic speech recognition
- hidden markov models
- speech recognition
- online learning
- acoustic models
- probabilistic model
- baum welch
- model selection
- markov models
- parameter estimation
- statistical models
- discriminatively trained
- data sets
- context sensitive
- experimental data
- complex systems
- test set
- contextual information
- context aware
- supervised learning
- multi class
- prior knowledge
- bayesian networks