HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch.
Tina RaissiWei ZhouSimon BergerRalf SchlüterHermann NeyPublished in: CoRR (2022)
Keyphrases
- automatic speech recognition
- hidden markov models
- speech recognition
- discriminative training
- speech signal
- word error rate
- acoustic models
- noisy environments
- broadcast news
- conversational speech
- speech retrieval
- spoken words
- speech corpus
- spontaneous speech
- language model
- acoustic features
- training process
- recognition errors
- training set
- pattern recognition
- speaker adaptation
- computer vision
- speaker identification
- word recognition
- speech synthesis
- bayesian networks
- image processing