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: CoRR (2021)
Keyphrases
- automatic speech recognition
- speech recognition
- hidden markov models
- acoustic models
- training set
- discriminatively trained
- statistical models
- test set
- training samples
- context sensitive
- parameter estimation
- machine learning algorithms
- graphical models
- class distribution
- support vector machine
- structured prediction
- probabilistic model
- machine learning