HMM vs. CTC for Automatic Speech Recognition: Comparison Based on Full-Sum Training from Scratch.
Tina RaissiWei ZhouSimon BergerRalf SchlüterHermann NeyPublished in: SLT (2022)
Keyphrases
- automatic speech recognition
- hidden markov models
- speech recognition
- discriminative training
- speech signal
- word error rate
- acoustic models
- conversational speech
- broadcast news
- speech retrieval
- speech corpus
- training set
- acoustic features
- recognition errors
- phoneme recognition
- spoken words
- training process
- speaker adaptation
- word recognition
- noisy environments
- language model
- information retrieval systems
- information retrieval